WO2023016044A1 - 视频处理方法、装置、电子设备和存储介质 - Google Patents
视频处理方法、装置、电子设备和存储介质 Download PDFInfo
- Publication number
- WO2023016044A1 WO2023016044A1 PCT/CN2022/094782 CN2022094782W WO2023016044A1 WO 2023016044 A1 WO2023016044 A1 WO 2023016044A1 CN 2022094782 W CN2022094782 W CN 2022094782W WO 2023016044 A1 WO2023016044 A1 WO 2023016044A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- video
- camera
- zoom
- exposure frame
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/63—Control of cameras or camera modules by using electronic viewfinders
- H04N23/631—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/63—Control of cameras or camera modules by using electronic viewfinders
- H04N23/631—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
- H04N23/632—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/741—Circuitry for compensating brightness variation in the scene by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/76—Circuitry for compensating brightness variation in the scene by influencing the image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10141—Special mode during image acquisition
- G06T2207/10144—Varying exposure
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
- H04N23/84—Camera processing pipelines; Components thereof for processing colour signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/79—Processing of colour television signals in connection with recording
Definitions
- the present application relates to the technical field of video shooting, and in particular to a video processing method, device, electronic equipment and storage medium.
- a video processing method, device, electronic equipment and storage medium which can improve the problem of low resolution caused by high scaling factor.
- a video processing method including: in a first zoom mode or a second zoom mode, acquiring a video captured by a camera, the video includes alternating first exposure frame video images and second exposure frame video images, The exposure time of the video image of the first exposure frame is greater than the exposure time of the video image of the second exposure frame; in the first zoom mode, the video image of the first exposure frame is processed by a super-resolution algorithm, and the super-resolution algorithm processing is used to improve the resolution; In the first zoom mode, the video image of the first exposure frame processed by the super-resolution algorithm is fused with the video image of the second exposure frame not processed by the super-resolution algorithm to obtain a fused video, and the video image of the first exposure frame has The first weight; in the second zoom mode, the first exposure frame video image and the second exposure frame video image are fused, the first exposure frame video image has a second weight, and the fused video is obtained, the first weight is greater than the first weight Two weights.
- the video processing method further includes: if the currently used camera is the first camera, and the shooting zoom factor belongs to the first zoom range, and the brightness of the current shooting picture is greater than the first brightness threshold, enter the first A zoom mode; if the currently used camera is the first camera, and the shooting zoom factor belongs to the second zoom range, and the second zoom range is smaller than the first zoom range, enter the second zoom mode; if the currently used camera is the first camera , and the shooting zoom factor belongs to the first zoom range, and the brightness of the current shooting picture is not greater than the first brightness threshold, then enter the second zoom mode.
- the first camera When using the first camera to shoot within the first zoom range, if the brightness of the current shooting picture is greater than the first brightness threshold, it is considered to be a non-dark scene, and enter the first zoom mode for video recording. If the brightness of the current shooting picture is not greater than When the first brightness threshold is reached, it is considered to be a dark scene, and enters the second zoom mode for video recording.
- the first camera is used to shoot in the lower second zoom range, even if it belongs to a non-dark scene, it still enters the second zoom mode. model. That is to say, for the same first camera, enter the first zoom mode when zooming at a high magnification in non-dark light.
- the super-resolution algorithm applied in the first zoom mode can be used to improve the resulting in low resolution problems.
- entering the second zoom mode does not need to use the super-resolution algorithm, nor does it need to reduce the fusion weight of the video image of the first exposure frame.
- the video processing method further includes: if the currently used camera is the second camera, and the shooting zoom factor belongs to the third zoom range, and the ISO of the camera belongs to the first ISO range, the third zoom range is smaller than the first ISO range.
- Second zoom range the focal length of the second camera is smaller than the focal length of the first camera, then enter the first zoom mode; if the currently used camera is the second camera, and the shooting zoom factor belongs to the third zoom range, and the camera ISO belongs to the second ISO range, and the brightness of the current shooting picture is greater than the second brightness threshold, and the second ISO range is greater than the first ISO range, then enter the second zoom mode; if the currently used camera is the second camera, and the zoom factor of the camera belongs to the fourth zoom range, the fourth zoom range is smaller than the third zoom range, and the brightness of the current shooting picture is greater than the third brightness threshold, then enter the second zoom mode.
- the video processing method further includes: if the currently used camera is the second camera, and the shooting zoom factor belongs to the second zoom range, and the brightness of the shooting picture is not greater than the fourth brightness threshold, enter the first Second zoom mode; if the currently used camera is the second camera, and the shooting zoom factor belongs to the second zoom range, and the shooting distance is less than the distance threshold, enter the second zoom mode; if the currently used camera is the second camera, and the shooting If the zoom factor belongs to the first zoom range, and the brightness of the shooting picture is not greater than the first brightness threshold, then enter the second zoom mode; if the currently used camera is the second camera, and the shooting zoom factor belongs to the first zoom range, and the shooting distance If it is smaller than the distance threshold, enter the first zoom mode.
- the super-resolution algorithm applied in the first zoom mode can be used to improve the due to Problem with low resolution due to high zoom factor.
- the video processing method further includes: in the first zoom mode, processing the fused video line through the logarithmic LOG curve corresponding to the current sensitivity ISO of the camera to obtain the LOG video;
- the lookup table LUT processes the LOG video to obtain the video processed by the LUT.
- the video recording process use the LUT technology of the film industry to process the LOG video based on the LUT corresponding to the determined video style template or the LUT corresponding to the first zoom mode, so that the recorded video has the determined video style template Corresponding style effects to meet higher color matching requirements.
- the video processing method further includes: performing super-resolution algorithm processing on the video image of the first exposure frame includes: acquiring statistical information corresponding to the video image of the first exposure frame; combining the statistical information and the video image of the first exposure frame
- the RAW image of the image is used as an input for super-resolution algorithm processing to obtain the processed RAW image of the video image of the first exposure frame.
- the logarithmic LOG curve corresponding to the current sensitivity ISO of the camera is used to process the fused video lines to obtain the LOG video, and based on the color lookup table
- the LUT processes the LOG video to obtain the process of the video processed by the LUT
- the video processing method also includes a second video processing flow, and the second video processing flow includes: the pair of logarithmic LOG curves corresponding to the current sensitivity ISO of the camera
- the fused video line is processed to obtain the LOG video
- the LOG video is processed based on the lookup table LUT to obtain the video processed by the LUT
- the video processing method also includes: saving the video processed by the LUT in the first video processing flow ; Preview the video after LUT processing in the second video processing flow.
- the preview video and the final video can have the same visual effect, which is convenient for the user to directly preview the video based on the color-graded style.
- a video processing device including: a processor and a memory, the memory is used to store at least one instruction, and when the instruction is loaded and executed by the processor, the above video processing method is implemented.
- an electronic device including: a camera; and the above-mentioned video processing device.
- a computer-readable storage medium In a fourth aspect, a computer-readable storage medium is provided.
- a computer program is stored in the computer-readable storage medium, and when running on a computer, the computer is made to execute the above video processing method.
- the video captured by the camera includes alternating first exposure frame video images and second exposure frame video images, wherein the exposure time of the first exposure frame video images is longer than The exposure time of the second exposure frame video image, in the first zoom mode, fuse the first exposure frame video image processed by the super-resolution algorithm and the second exposure frame video image without the super-resolution algorithm processing, in the second In the zoom mode, the video image of the first exposure frame and the video image of the second exposure frame are fused. Compared with the second zoom mode, in the first zoom mode, the video image of the first exposure frame has a larger fusion weight.
- the improvement in the first zoom mode is longer The fusion weight of the image at the exposure time, so that the fused image can more clearly reflect the effect of the super-resolution algorithm, and improve the problem of low resolution caused by the high zoom factor.
- FIG. 1 is a structural block diagram of an electronic device in an embodiment of the present application
- FIG. 2 is a flowchart of a video processing method in an embodiment of the present application
- FIG. 3 is a flow chart of another video processing method in the embodiment of the present application.
- Fig. 4 is the schematic diagram of a kind of LOG curve in the embodiment of the present application.
- FIG. 5 is a schematic diagram of a user interface in a movie mode in an embodiment of the present application.
- FIG. 6 is a partial flowchart of another video processing method in the embodiment of the present application.
- FIG. 7 is a schematic diagram of the relationship between a cube and a tetrahedron in a cube interpolation space in an embodiment of the present application
- Fig. 8 is a UV plane schematic diagram
- FIG. 9 is another structural block diagram of an electronic device in the embodiment of the present application.
- FIG. 10 is a software structural block diagram of an electronic device in an embodiment of the present application.
- FIG. 11 is a schematic diagram of a user interface in a professional mode in an embodiment of the present application.
- the electronic device 100 may include a processor 110, a camera 193, a display screen 194, and the like. It can be understood that, the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100 . In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine certain components, or separate certain components, or arrange different components. The illustrated components can be realized in hardware, software or a combination of software and hardware.
- the processor 110 may include one or more processing units, for example: the processor 110 may include a graphics processing unit (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a video codec, Digital signal processor (digital signal processor, DSP), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.
- the controller can generate an operation control signal according to the instruction opcode and timing signal, and complete the control of fetching and executing the instruction.
- a memory may also be provided in the processor 110 for storing instructions and data.
- the electronic device 100 realizes the display function through the GPU, the display screen 194 , and the application processor.
- the GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering.
- Processor 110 may include one or more GPUs that execute program instructions to generate or change display information.
- the electronic device 100 can realize the shooting function through the ISP, the camera 193 , the video codec, the GPU, the display screen 194 and the application processor.
- the ISP is used for processing the data fed back by the camera 193 .
- the light is transmitted to the photosensitive element of the camera through the lens, and the light signal is converted into an electrical signal, and the photosensitive element of the camera transmits the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye.
- ISP can also perform algorithm optimization on image noise, brightness, and skin color.
- ISP can also optimize the exposure, color temperature and other parameters of the shooting scene.
- the ISP may be located in the camera 193 .
- Camera 193 is used to capture still images or video.
- the object generates an optical image through the lens and projects it to the photosensitive element.
- the photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor.
- CMOS complementary metal-oxide-semiconductor
- the photosensitive element converts the light signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal.
- the ISP outputs the digital image signal to the DSP for processing.
- DSP converts digital image signals into standard RGB, YUV and other image signals.
- the electronic device 100 may include 1 or N cameras 193 , where N is a positive integer greater than 1.
- Digital signal processors are used to process digital signals. In addition to digital image signals, they can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the energy of the frequency point.
- Video codecs are used to compress or decompress digital video.
- the electronic device 100 may support one or more video codecs.
- the electronic device 100 can play or record videos in various encoding formats, for example: moving picture experts group (moving picture experts group, MPEG) 1, MPEG2, MPEG3, MPEG4 and so on.
- MPEG moving picture experts group
- the embodiment of the present application provides a video processing method.
- the video processing method may be executed by a processor 110, specifically an ISP or a combination of an ISP and other processors.
- the video processing method includes:
- step 101 obtain the video shot by the camera, the video includes alternating first exposure frame video images and second exposure frame video images, and the exposure time of the first exposure frame video images greater than the exposure time of the second exposure frame video image;
- the first zoom mode and the second zoom mode can be switched based on the user's selection, or can be automatically judged and switched based on the current picture of the video captured by the camera on the basis of the user's selection. Alternately use different exposure times for shooting, so as to facilitate subsequent fusion of video images based on different exposure times.
- step 102 perform super-resolution algorithm processing on the video image of the first exposure frame, and the super-resolution algorithm processing is used to improve the resolution;
- the first zoom mode is a mode suitable for a larger zoom factor.
- the higher zoom factor may cause the resolution of the shooting picture to be lower.
- the super-resolution algorithm is an underlying image processing algorithm that can map low-resolution images to high-resolution images in order to enhance image details.
- the super-resolution algorithm can be a method algorithm based on deep learning. First, it uses a large number of high-resolution images to accumulate and learn, and then learns low-resolution images. The learning model of high-resolution images is introduced for restoration, and finally the image is obtained. The high-frequency details can obtain better image restoration effect. Improve image recognition ability and recognition accuracy.
- the camera captures the video image of the first exposure frame and the video image of the second exposure frame at a relatively high frequency. Therefore, it may not be possible to apply the super-resolution algorithm to both the video image of the first exposure frame and the video image of the second exposure frame.
- the video image of the first exposure frame is selected for super-resolution algorithm processing , the video image of the second exposure frame is not processed by the super-resolution algorithm, so that the application of the super-resolution algorithm can be realized within an effective time;
- step 103 In the first zoom mode, go to step 103 to fuse the video image of the first exposure frame processed by the super-resolution algorithm and the video image of the second exposure frame not processed by the super-resolution algorithm to obtain the fused video, the first exposure
- the frame video image has a first weight
- every adjacent first exposure frame video image and second exposure frame video image are fused into a new frame of video image, and the fused video image includes the first exposure frame video image and
- the information in the video image of the second exposure frame, the fusion weight of the two frames of images can be adjusted, the video image of the first exposure frame has the first weight, that is to say, the fusion weight occupied by the video image of the first exposure frame in the two frames , the larger the first weight is, the more information the first exposure frame video image contains in the fused video image, and correspondingly, the smaller the weight occupied by the second exposure frame video image is, that is, the information of the fused video image
- the second video frame contains less information.
- step 104 In the second zoom mode, enter step 104, and fuse the video image of the first exposure frame and the video image of the second exposure frame.
- the video image of the first exposure frame has a second weight to obtain the fused video.
- the first weight is greater than the second weight. Two weights.
- the first weight is 70% and the second weight is 50%
- the second zoom mode in the process of fusing the video image of the first exposure frame and the video image of the second exposure frame, according to each 50%
- the weight of the fusion is performed, and the fused video image contains 50% of the information in the first exposure frame video image and 50% of the information in the second exposure frame video image; in the first zoom mode, the first exposure frame video
- the fusion is carried out according to the weight of 70% of the video image of the first exposure frame and the weight of 30% of the video image of the second exposure frame, and the fused video image contains 70% of the first The information in the exposed frame video image and 30% of the information in the second exposed frame video image.
- the video image of the first exposure frame has a larger fusion weight.
- the fused video image can more clearly reflect the effect of processing through the super-resolution algorithm.
- related video processing may continue to be performed to complete video recording.
- the video captured by the camera includes alternating first exposure frame video images and second exposure frame video images, wherein the exposure time of the first exposure frame video images is longer than the exposure time of the second exposure frame video images Time, in the first zoom mode, fuse the video image of the first exposure frame processed by the super-resolution algorithm with the video image of the second exposure frame not processed by the super-resolution algorithm, and in the second zoom mode, fuse the video image of the first exposure frame
- the frame video image is fused with the second exposure frame video image.
- the first exposure frame video image has a larger fusion weight.
- the fusion weight of the image with a longer exposure time is increased in the first zoom mode. In order to make the fused image more clearly reflect the effect of the super-resolution algorithm, and improve the problem of low resolution caused by the high zoom factor.
- the video processing method further includes: if the currently used camera is the first camera, and the shooting zoom factor belongs to the first zoom range, and the brightness of the current shooting picture is greater than the first brightness threshold, enter the first A zoom mode; if the currently used camera is the first camera, and the shooting zoom factor belongs to the second zoom range, and the second zoom range is smaller than the first zoom range, enter the second zoom mode; if the currently used camera is the first camera , and the shooting zoom factor belongs to the first zoom range, and the brightness of the current shooting picture is not greater than the first brightness threshold, then enter the second zoom mode.
- the shooting zoom factor is related to the equivalent focal length.
- the first zoom range is (7x, 15x]
- x represents the multiple, that is, the first zoom range is 7 times to 15 times, including 10 times
- the extreme point and the extreme point of 15 times, the equivalent focal length range corresponding to the first zoom range is greater than 190mm;
- the second zoom range is [3.5x, 7x), that is, the second zoom range is 3.5 times to 7 times, Including the extreme point of 3.5 times, excluding the extreme point of 7 times, the equivalent focal length range corresponding to the second zoom range is [95mm, 190mm).
- An electronic device such as a mobile phone, may have multiple cameras, and the first camera may be, for example, a telephoto camera.
- Table 1 illustrates a zoom mode corresponding to different parameters in the embodiment of the present application.
- the super-resolution algorithm applied in the first zoom mode can be used to improve the resulting in low resolution problems.
- entering the second zoom mode does not need to use the super-resolution algorithm, nor does it need to reduce the fusion weight of the video image of the first exposure frame.
- the video processing method further includes: if the currently used camera is the second camera, and the shooting zoom factor belongs to the third zoom range, and the ISO of the camera belongs to the first ISO range, the third zoom range is smaller than the first ISO range.
- Second zoom range the focal length of the second camera is smaller than the focal length of the first camera, then enter the first zoom mode; if the currently used camera is the second camera, and the shooting zoom factor belongs to the third zoom range, and the camera ISO belongs to the second ISO range, and the brightness of the current shooting picture is greater than the second brightness threshold, and the second ISO range is greater than the first ISO range, then enter the second zoom mode; if the currently used camera is the second camera, and the zoom factor of the camera belongs to the fourth zoom range, the fourth zoom range is smaller than the third zoom range, and the brightness of the current shooting picture is greater than the third brightness threshold, then enter the second zoom mode.
- the fourth zoom range is [1x, 1.8x], that is, the fourth zoom range is 1x to 1.8x, including extreme points, and the equivalent focal length range corresponding to the fourth zoom range is (27mm, 48mm).
- the second camera is the main camera in the mobile phone, the focal length of the main camera is smaller than that of the telephoto camera.
- the first ISO range is less than or equal to 1600, and the second ISO range is greater than 1600.
- the second camera uses the second ISO range
- in the third zoom range if the brightness of the current shooting picture is greater than the second brightness threshold, it is considered to belong to a non-low light scene; otherwise, if the brightness of the current shooting picture is not greater than the second brightness threshold
- the fourth zoom range if the brightness of the current shooting picture is greater than the third brightness threshold, it is considered to be a non-low light scene.
- the second brightness threshold may be equal to or not equal to the third brightness threshold.
- the embodiment of the present application does not limit the specific implementation of the third zoom mode.
- image processing can be further optimized for low-light scenes.
- the embodiment of the present application does not limit the specific image processing process of the second zoom mode. In the second zoom mode, it can be further divided into different sub-modes to apply different algorithm processing.
- OIS Optical Image Stabilization
- EIS Electronic Image Stabilization
- Table 1 it can be seen that the second camera can also work in the fifth zoom range, the fifth zoom range is [0.9x, 1x), and the corresponding equivalent focal length range is [23mm, 27mm), at this time, in The above-mentioned second zoom mode can be entered in the whole scene.
- the electronic device in the embodiment of the present application also includes a third camera, the third camera can be a super wide-angle camera, the focal length of the third camera is smaller than the focal length of the second camera, the third camera can work with the sixth zoom range, the sixth zoom range is [0.4x, 0.9x), and the corresponding equivalent focal length range is [11mm, 23mm).
- the video processing method further includes: if the currently used camera is the second camera, and the shooting zoom factor belongs to the second zoom range, and the brightness of the shooting picture is not greater than the fourth brightness threshold, enter the first Second zoom mode; if the currently used camera is the second camera, and the shooting zoom factor belongs to the second zoom range, and the shooting distance is less than the distance threshold, enter the second zoom mode; if the currently used camera is the second camera, and the shooting If the zoom factor belongs to the first zoom range, and the brightness of the shooting picture is not greater than the first brightness threshold, then enter the second zoom mode; if the currently used camera is the second camera, and the shooting zoom factor belongs to the first zoom range, and the shooting distance If it is smaller than the distance threshold, enter the first zoom mode.
- the second camera when the second camera applies the second zoom range, it can be applied to dark scenes, that is, the brightness of the current shooting picture is not greater than the fourth brightness threshold, and the fourth brightness threshold can be the same as other brightness thresholds, or can be different from other brightness thresholds.
- you can enter the second zoom mode and it can also be applied to close-up shooting scenarios, that is, the shooting distance is less than the preset distance, for example, the shooting distance is ⁇ 1200cm, which can be considered as a close-up shooting scene, and you can enter the second zoom mode at this time.
- Two zoom modes Two zoom modes.
- the second camera When the second camera uses the first zoom range, it can be applied to a dark scene, that is, the brightness of the currently captured image is not greater than the first brightness threshold, and at this time, the second zoom mode can be entered.
- the second camera uses the first zoom range, it can be applied to a close-range shooting scene, for example, the shooting distance is ⁇ 1200 cm, and at this time, the first zoom scene can be entered. That is to say, in the close-up shooting scene of the second camera in the first zoom range and the second zoom range, if the zoom factor is relatively high, that is, it belongs to the first zoom range, the super zoom applied in the first zoom mode can The sub-algorithm improves the problem of low resolution due to high zoom factor.
- the video processing method further includes:
- step 105 process the fused video line through the logarithmic LOG curve corresponding to the current sensitivity ISO of the camera, and obtain the LOG video;
- Figure 4 illustrates a LOG curve, where the abscissa is a linear signal, represented by a 16-bit code value Code Value, and the ordinate is the LOG signal processed by the LOG curve, represented by a 10-bit code value.
- the signal input of the camera can be used to encode the information in the dark area to the middle tone (as shown in the steep part of the curve in Figure 4), forming a 10-bit signal output, which conforms to the human eye's LOG sensing rule for light, and maximizes the The dark information is preserved, and the LOG video can use the limited bit depth to maximize the details of shadows and highlights.
- the ASA in Figure 4 is the sensitivity, and different ASAs correspond to different ISOs, and the two belong to different standards.
- Step 106 process the LOG video based on the color look-up table (Look Up Table, LUT), and obtain the video processed by the LUT.
- LUT Color look-up table
- the essence of LUT is a mathematical conversion model, by using LUT, one set of RGB values can be output as another set of RGB values, thereby changing the exposure and color of the picture.
- the first zoom mode for example, there are two LUT-based processing methods. One is to only use the LUT to process the video according to the characteristics of the scene. In this method, the corresponding LUT; the other is to use LUT to apply different video styles, the following will take the second method as an example to illustrate. LUTs corresponding to different video styles can be pre-generated. Before the electronic device records a video, a video style template can be determined first.
- the video style template can be determined based on the user's choice, or based on artificial intelligence (AI), according to the current
- AI artificial intelligence
- the user operates the mobile phone to enter the shooting interface in the first zoom mode.
- the movie mode in the corresponding movie mode interface, including multiple video style template options, for example including "A" movie style template, "B" movie style template and "C” movie style template
- the user interface shown in Figure 5 Only one "A" movie style template is shown in . It is understandable that multiple different movie style templates can be displayed side by side in the user interface.
- the LUTs corresponding to different movie style templates can be pre-generated based on the corresponding movie color matching style.
- the color conversion of LUT has the style characteristics of the corresponding movie.
- the color matching style of "A" movie is complementary color.
- Complementary color refers to the contrast effect of two corresponding colors. Emphasize the contrast to enhance the bright and prominent effect. Usually, two contrasting colors symbolize conflicting behaviors. Through the presentation of external complementary colors, it can be used to express the character's inner conflict or exhausted state.
- "A" movie style template The corresponding LUT is used to convert the color mapping to make the complementary colors more obvious, so as to simulate the color matching style of the "A" movie.
- the mobile phone when the user operates the mobile phone to enter the movie mode, the mobile phone will obtain the picture taken by the current camera, and based on the AI algorithm, determine the scene corresponding to the picture and determine the scene corresponding to the scene.
- the recommended video style template for example, if it is recognized that the subject of the currently captured picture is a young female character, the corresponding recommended video style template is determined according to the algorithm as the "C" movie style template, and the movie "C" has a young female character as the theme movie, its corresponding LUT can simulate the color matching style of the movie "C"; It is a movie with city streets as the main scene, and its corresponding LUT can simulate the color matching style of the "B” movie. In this way, a video style template matching the current scene can be automatically recommended for the user. Film styles can be pre-extracted to produce LUTs suitable for mobile electronics.
- Different LUTs are applied to electronic equipment, and related modules in the electronic equipment can be adapted to adapt to different styles of LUTs.
- the predetermined video style template is a gray-tone video style template
- the characteristics of gray-tone images In order to make the picture have a strong sense of texture, low saturation, no more color interference except for the color of the character's skin, and cooler dark parts, based on these characteristics, the electronic device can adjust the relevant module parameters during the video recording process. Make adjustments to keep the texture in the picture, do not do strong denoising and sharpening, properly reduce the saturation of the picture, keep the skin color in the picture true to restore, and adjust the dark part of the picture to cool colors.
- the LUT technology of the film industry is used to process the LOG video based on the LUT corresponding to the determined video style template or the LUT corresponding to the first zoom mode, so that all The recorded video has the style effect corresponding to the determined video style template, so as to meet the higher color grading requirements.
- performing super-resolution algorithm processing on the video image of the first exposure frame includes: acquiring statistical information corresponding to the video image of the first exposure frame;
- the RAW image of an exposure frame video image is used as an input to perform super-resolution algorithm processing, and the processed RAW image of the first exposure frame video image is obtained.
- the RAW image is the original data that the sensor in the camera converts the captured light source signal into a digital signal.
- the electronic device includes a camera 193, a super-resolution algorithm module 31 and a statistical information acquisition module 32, wherein the statistical information acquisition Module 32 can be the module in ISP, obtains first exposure frame video image and second exposure frame video image by camera 193 in step 101, and this first exposure frame video image is transmitted to statistical information acquisition module 32 and super Sub-algorithm module 31, wherein, statistical information acquisition module 32 obtains the stats statistical information corresponding to the image according to the first exposure frame video image, and transmits the statistical information to the super-resolution algorithm module 31, and transmits it to the super-resolution algorithm module 31
- the first exposure frame video image can be a RAW image
- the super-resolution algorithm module 31 uses the RAW image as input, and simultaneously processes the first frame of video image based on the obtained corresponding statistical information, obtains the processed RAW image and outputs it to the subsequent process.
- the super-resolution algorithm module 31 performs the process of super-resolution algorithm processing in the RAW domain during the entire image processing process.
- the process of super-resolution algorithm processing It can also be done eg in the YUV domain.
- Bayer field Each lens on a digital camera has a light sensor to measure the brightness of the light, but to obtain a full-color image, generally three light sensors are required to obtain the three primary colors of red, green and blue information, and in order to reduce the cost and volume of digital cameras, manufacturers usually use CCD or CMOS image sensors.
- CCD or CMOS image sensors usually use CCD or CMOS image sensors.
- the original image output by CMOS image sensors is in Bayer domain RGB format, and a single pixel contains only one color value. To obtain the gray value of the image, it is necessary to interpolate the complete color information of each pixel, and then calculate the gray value of each pixel.
- the Bayer domain refers to a raw image format inside a digital camera.
- the Raw domain or Raw format refers to unprocessed images. Further, the Raw image can be understood as that the photosensitive element of the camera such as Complementary Metal Oxide Semiconductor (Complementary Metal Oxide Semiconductor, CMOS) or Charge-coupled Device (Charge-coupled Device, CCD) converts the captured light source signal into digital The raw data of the signal.
- CMOS Complementary Metal Oxide Semiconductor
- CCD Charge-coupled Device
- a RAW file is a record of the original information of the digital camera sensor, while recording some metadata (Metadata, such as ISO (International Organization for Standardization, International Organization for Standardization) settings, shutter speed, aperture value) generated by the camera. , white balance, etc.) files.
- the Raw domain is a format that has not been processed by the ISP nonlinearly and has not been compressed.
- the full name of Raw format is RAW Image Format.
- YUV is a color encoding method that is often used in various video processing components. YUV takes human perception into account when encoding photos or videos, allowing bandwidth reduction for chroma. YUV is a type of compiling true-color color space (color space). The proper nouns such as Y'UV, YUV, YCbCr, and YPbPr can all be called YUV, and they overlap with each other. Among them, "Y” represents the brightness (Luminance or Luma), that is, the grayscale value, "U” and “V” represent the chroma (Chrominance or Chroma), which are used to describe the color and saturation of the image, and are used to specify the color of the pixel .
- YUV is divided into two formats, one is: packed formats, which store Y, U, and V values into a Macro Pixels array, which is similar to the storage method of RGB.
- the other is: planar formats, which store the three components of Y, U, and V in different matrices.
- Planar formats means that each Y component, U component and V component are organized in an independent plane, that is to say, all U components are behind the Y component, and V components are behind all U components.
- step 106 process LOG video based on color lookup table (Look Up Table, LUT), the process of obtaining the video after LUT processing comprises:
- 3D-LUT is a color mapping relationship commonly used in the film industry. It can convert any input RGB pixel value into corresponding other RGB pixel values, such as inputting 12bit RGB Video image, output 12bit RGB video image after LUT processing and mapping.
- the LOG video is used as the input in the LUT processing process, and the pixel points mapped by the LUT processing are obtained for each pixel in the LOG video screen, which can realize the process of processing the LOG video through the LUT.
- Each pixel in the LOG video belongs to the cube in the above cube interpolation space, and the cube is divided into 6 tetrahedrons.
- the pixel value is converted to the pixel value processed by LUT.
- interpolation is performed according to the tetrahedron to which each pixel point belongs, and the pixel value is converted to the pixel value processed by LUT. After the pixel value.
- the mapped RGB pixel value can be directly obtained, that is, the pixel value can be directly mapped and converted into The corresponding pixel value, and if the pixel is located between the vertices of the cube, interpolate according to the tetrahedron to which the pixel belongs.
- the cube has the 0th to 7th vertices, which are represented by numbers 0 to 7 in Figure 7, and the direction from the 0th vertex to the first vertex is blue B
- the coordinate axis direction of the channel, the direction from the 0th vertex to the 4th vertex is the coordinate axis direction of the red R channel
- the direction from the 0th vertex to the second vertex is the coordinate axis direction of the green G channel
- the 2nd vertex and the 3rd vertex are located on the same plane
- the 1st vertex, the 3rd vertex, the 5th vertex and the 7th vertex are located on the same plane
- the 4th vertex, the 5th vertex, the 6th vertex and the 7th vertex are located on the same plane
- the 3rd vertex is located on the same plane.
- Vertex 0, Vertex 2, Vertex 4 and Vertex 6 are on the same plane; Vertex 0, Vertex 1, Vertex 5 and Vertex 7 form the first tetrahedron, Vertex 0, Vertex 1, Vertex 3
- the vertex and the 7th vertex form the second tetrahedron, the 0th vertex, the 2nd vertex, the 3rd vertex and the 7th vertex form the third tetrahedron, the 0th vertex, the 4th vertex, the 5th vertex and the 7th vertex form
- the 0th vertex, the 4th vertex, the 6th vertex and the 7th vertex form the fifth tetrahedron
- the 0th vertex, the 2nd vertex, the 6th vertex and the 7th vertex form the sixth tetrahedron;
- the coordinates of the i-th vertex are (Ri, Gi, Bi)
- the value of i is 0, 1, 2, 3, ..., 7, and the pixel value of the pixel value of the
- the above-mentioned pixel points that do not correspond to the vertices of the cube are interpolated according to the tetrahedron to which each pixel point belongs, and the process of converting the pixel value into the pixel value after LUT processing includes:
- VE(R, G, B) VE(R0, G0, B0)+(delta_valueR_E ⁇ deltaR+delta_valueG_E ⁇ deltaG+delta_valueB_E ⁇ deltaB+(step_size>1))/(step_size);
- VE(R0, G0, B0) is the E channel pixel value of the 0th vertex (R0, G0, B0) after LUT processing, and E is R, G and B;
- delta_valueR_E is the difference between the two vertices in the direction of the coordinate axis of the R channel corresponding to the tetrahedron to which the current pixel belongs, and the difference between the pixel values of the E channel after LUT processing.
- delta_valueB_E is the difference between the pixel values of the E channel after the LUT processing of two vertices in the direction of the coordinate axis of the tetrahedron to which the current pixel belongs corresponding to the B channel;
- deltaR is the difference between the R value in the current pixel point (R, G, B) and the R0 value in the 0th vertex (R0, G0, B0)
- deltaG is the G value in the current pixel point (R, G, B).
- deltaB is the difference between the B value in the current pixel point (R, G, B) and the B0 value in the 0th vertex (R0, G0, B0).
- step_size is the side length of the cube.
- step_size>>1 means step_size is shifted to the right by one bit.
- deltaR R-R0
- deltaG G-G0
- deltaB B-B0
- which tetrahedron the current pixel belongs to can be judged according to the relationship between deltaR, deltaG and deltaB.
- deltaB ⁇ deltaR and deltaR ⁇ deltaG determine that the current pixel belongs to the first tetrahedron; if deltaB ⁇ deltaG and deltaG ⁇ deltaR, determine that the current pixel belongs to the second tetrahedron; if deltaG ⁇ deltaB and deltaB ⁇ deltaR , it is determined that the current pixel point belongs to the third tetrahedron; if deltaR ⁇ deltaB and deltaB ⁇ deltaG, then it is determined that the current pixel point belongs to the fourth tetrahedron; if deltaR ⁇ deltaG and deltaG ⁇ deltaB, then it is determined that the current pixel point belongs to the fourth tetrahedron Five tetrahedrons; if the relationship among deltaR, deltaG, and deltaB does not belong to the above conditions of the first to fifth tetrahedrons, it is determined that the current pixel point belongs to the sixth tetrahedron.
- delta_valueR_E is the tetrahedron to which the current pixel point belongs
- delta_valueR_R VR(R5, G5, B5)-VR(R1, G1, B1)
- delta_valueG_R VR( R7, G7, B7)-VR(R5, G5, B5)
- delta_valueB_R VR(R1, G1, B1)-VR(R0, G0, B0)
- VR(R, G, B) VR(R0, G0 , B0)+(delta_valueR_R ⁇ deltaR+delta_valueG_R ⁇ deltaG+delta_valueB_R ⁇ deltaB+
- the process of processing the LOG video based on the color look-up table (Look Up Table, LUT) in the above step 106 to obtain the video processed by the LUT it also includes: converting the LOG video from RGB
- the LOG video of color space is converted into the LOG video of YUV color space;
- the LOG video of YUV color space is carried out YUV denoising process, obtains the LOG video after denoising, applies the LOG video of LUT to be through YUV denoising in step 106 After the LOG video.
- the LOG video obtained in step 105 can reflect the details of the dark part, but at the same time, the noise of the dark part will be amplified, that is, noise will be introduced. Therefore, after the LOG video can be converted into a YUV color space, YUV denoising can be performed, and the noise can be reduced through an algorithm. to improve video image quality.
- the process of processing the LOG video based on the color look-up table (Look Up Table, LUT) to obtain the video after LUT processing in the above step 106 it also includes: denoising the LOG video is converted into the LOG video of RGB color space by the LOG video of YUV color space;
- LOG video is processed, obtain after the process of the video after LUT processing , also includes: converting the LUT-processed video in the RGB color space to a video in the YUV color space.
- step 106 Because the process of processing the LOG video based on the LUT in step 106 is realized based on the RGB color space, therefore, before the step 105, the video in the YUV color space is converted to the video in the RGB color space, and after the step 106, then Reconvert video in RGB color space to video in YUV color space.
- YUV also known as YCbCr
- YCbCr is a color coding method used by the European television system.
- three-tube color cameras or color CCD cameras are usually used to capture images, and then the obtained color image signals are separated, amplified and corrected to obtain RGB signals, and then the brightness signals Y and Y are obtained through a matrix conversion circuit.
- Two color-difference signals B-Y (ie U) and R-Y (ie V), and finally the sending end encodes the three signals separately and sends them out on the same channel.
- This color representation method is the YUV color space.
- YCbCr is the specific implementation of the YUV model, which is actually a scaled and offset replica of YUV.
- Y has the same meaning as Y in YUV, and both Cb and Cr refer to color, but they are different in the way of expression.
- YCbCr is the most widely used member in computer systems, and its application fields are very wide. Both JPEG and MPEG use this format. Generally speaking, YUV mostly refers to YCbCr.
- the UV plane is shown in Figure 8.
- RGB and YUV color spaces can be realized by a 3x3 matrix:
- the electronic device may specifically include a camera 193, a super-resolution algorithm module 31, a statistical information acquisition module 32, an anti-mosaic Demosaic module 21, a deformation module 22, a fusion module 23, a noise Processing module 24, color correction matrix (Color Correction Matrix, CCM) module 25, global tone mapping (Global Tone Mapping, GTM) module 26, scaling Scaler module 27, YUV denoising module 28, LUT processing module 29, for example, in video
- the camera 193 captures the video image of the first exposure frame and the video image of the second exposure frame, and the exposure time corresponding to the video image of the first exposure frame is longer than the exposure time corresponding to the video image of the second exposure frame.
- the statistical information acquisition module 32 obtains the statistical information corresponding to the video image of the first exposure frame
- the super-resolution algorithm module 31 uses the statistical information and the RAW image of the video image of the first exposure frame as input to perform super-resolution algorithm processing, and obtains the super-resolution algorithm.
- the RAW image of the first exposure frame video image processed by the sub-algorithm, the first exposure frame video image after the super-resolution algorithm processing and the second exposure frame video image without the super-resolution algorithm processing are respectively processed by the anti-mosaic module 21 , the image is converted from the RAW domain to the RGB domain, and then the two-way video images are processed by the deformation warp module 22 respectively, and the effects of alignment and anti-shake are realized through the deformation of the video images, and then the two-way video images are processed by the fusion module 23,
- the two video images are fused into one, and the fused data is divided into two paths.
- the video processing method includes a first video processing flow S1 and a second video processing flow S2, and one of the paths processed by the fusion module 23 enters the first The video processing flow S1, another way enters the second video processing flow S2.
- the process of converting the video captured by the camera into a video in a wide color gamut color space processing the video through a logarithmic LOG curve to obtain a LOG video, and processing the LOG video based on the LUT The process of processing.
- the first video processing flow S1 includes, the video taken by the camera 193 from the fusion module 23 is denoised by the noise processing module 24, and then processed by the CCM module 25 to convert the video into RGB wide color gamut color space, and then the logarithmic LOG curve corresponding to the current sensitivity ISO of the camera is used to process the fused video line through the GTM module 26 to obtain the process of the LOG video, and then the video is zoomed through the scaling module 27, and then through the YUV
- the denoising module 28 performs YUV denoising on the video, and then the LOG video is processed based on the color lookup table LUT through the LUT processing module 29 to obtain the video processed by the LUT.
- the video after the LUT processing in the first video processing flow S1 is saved as a video.
- the second video processing flow S2 includes: the video taken by the camera 193 from the fusion module 23 is denoised by the noise processing module 24, and then processed by the CCM module 25 to convert the video into the color space of RGB wide color gamut, Then the logarithmic LOG curve corresponding to the current sensitivity ISO of the camera is used to process the fused video line by the GTM module 26 to obtain the process of the LOG video, and then the video is zoomed by the zoom module 27, and then by YUV
- the denoising module 28 performs YUV denoising on the video, and then executes the process of processing the LOG video based on the lookup table LUT through the LUT processing module 29 to obtain the video processed by the LUT.
- the video after the LUT processing in the second video processing flow S2 is previewed.
- the above only illustrates the specific video recording process in the first zoom mode. You can switch to the second zoom mode during the recording process or before two recordings. In the second zoom mode, no super-resolution algorithm processing is performed.
- the first The exposure frame video image and the second exposure frame video image are respectively processed by the anti-mosaic module 21 to convert the image from the RAW domain to the RGB domain, and then the two channels of video images are respectively processed by the warp warp module 22 to deform the video image.
- the effect of alignment and anti-shake is realized, and then the two-way video images are processed by the fusion module 23, and the two video images are fused into the same one.
- the fusion weight of the video image of the first exposure frame is smaller than that of the first zoom mode
- the fusion weight of the first exposure frame video image, the video image processing process after fusion in the second zoom mode may be the same as the first zoom mode, or different from the first zoom mode, which is not limited in the embodiment of the present application .
- FIG. 10 is a block diagram of the software structure of the electronic device 100 according to the embodiment of the present application.
- the layered architecture divides the software into several layers, and each layer has a clear role and division of labor. Layers communicate through software interfaces.
- the Android system is divided into five layers, which are, from top to bottom, the Application layer, the application framework framework layer, the system library library, the Hardware Abstraction Layer (Hardware Abstraction Layer, HAL) and the kernel layer.
- the application layer can include applications such as cameras.
- the application framework layer may include camera application programming interface (Application Programming Interface, API), media recording MediaRecorder and surface view Surfaceview, etc.
- Media recording is used to record video or image data and make this data accessible to applications.
- Surface views are used to display preview images.
- a system library can include multiple function modules. For example: camera service CameraSevice, etc.
- the hardware abstraction layer is used to provide interface support, for example, including the camera process CameraPipeline for the camera service to call Call.
- the kernel layer is the layer between hardware and software.
- the kernel layer includes display drivers, camera drivers, etc.
- the application layer sends a capture request CaptureRequest, which corresponds to a video stream and a preview stream.
- CaptureRequest corresponds to a video stream and a preview stream.
- HAL calls back two streams according to the dataflow mentioned above. Among them, the preview streaming display, the video streaming mediacodec.
- the video recording and video processing method provided in the embodiment of the present application may be represented as multiple functions in two shooting modes, where the two shooting modes may refer to: movie mode and professional mode.
- the movie mode is a shooting mode related to the theme of the movie.
- the image displayed by the electronic device 100 can give the user a sense of watching a movie.
- the electronic device 100 also provides a plurality of video related to the theme of the movie Style templates, users can use these video style templates to obtain tone-adjusted images or videos, and the tone of these images or videos is similar or identical to the tone of the movie.
- the movie mode can at least provide an interface for the user to trigger the LUT function and the HDR10 function. For specific descriptions about the LUT function and the HDR10 function, please refer to the following embodiments.
- the electronic device 100 may enter a movie mode in response to a user's operation.
- the electronic device 100 may detect a user's touch operation on the camera application, and in response to the operation, the electronic device 100 displays a default camera interface of the camera application.
- the default camera interface can include: preview frame, shooting mode list, gallery shortcut keys, shutter controls, etc. in:
- the preview frame can be used to display images collected by the camera 193 in real time.
- the electronic device 100 can refresh the displayed content therein in real time, so that the user can preview the image currently captured by the camera 193 .
- One or more shooting mode options may be displayed in the shooting mode list.
- the one or more shooting mode options may include: portrait mode options, video recording mode options, camera mode options, movie mode options, and professional options.
- the one or more shooting mode options can be represented as text information on the interface, such as "portrait”, “video recording”, “photographing”, “movie”, “professional”.
- the one or more shooting mode options may also be represented as icons or other forms of interactive elements (interactive element, IE) on the interface.
- Gallery shortcuts can be used to launch the Gallery application.
- the gallery application program is an application program for picture management on electronic devices such as smart phones and tablet computers, and may also be called "album".
- the name of the application program is not limited in this embodiment.
- the gallery application program can support users to perform various operations on pictures stored on the electronic device 100, such as browsing, editing, deleting, selecting and other operations.
- the shutter control can be used to listen for user actions that trigger a photo.
- the electronic device 100 may detect a user operation acting on the shutter control, and in response to the operation, the electronic device 100 may save the image in the preview frame as a picture in the gallery application.
- the electronic device 100 may also display the thumbnails of the saved images in the gallery shortcut key. That is, users can tap the shutter control to trigger a photo.
- the shutter control may be a button or other forms of control.
- the electronic device 100 may detect a user's touch operation on the movie mode option, and in response to the operation, the electronic device displays a user interface as shown in FIG. 5 .
- the electronic device 100 may turn on the movie mode by default after starting the camera application. Not limited thereto, the electronic device 100 may also enable the movie mode in other ways, for example, the electronic device 100 may also enable the movie mode according to a user's voice command, which is not limited in this embodiment of the present application.
- the electronic device 100 may detect a user's touch operation on the movie mode option, and in response to the operation, the electronic device displays a user interface as shown in FIG. 5 .
- the user interface shown in FIG. 5 includes function options, and the function options include HDR10 options, flash options, LUT options, and setting options. These multiple function options can detect the user's touch operation, and in response to the operation, enable or disable the corresponding shooting function, for example, HDR10 function, flash function, LUT function, setting function.
- the electronic device can enable the LUT function, and the LUT function can change the display effect of the preview image.
- the LUT function introduces a color lookup table, which is equivalent to a color conversion model, which can output adjusted color values according to the input color values.
- the color value of the image captured by the camera is equivalent to the input value, and different color values can be correspondingly obtained as an output value after passing through the color conversion model.
- the image displayed in the preview box is the image adjusted by the color transformation model.
- the electronic device 100 utilizes the LUT function to display an image composed of color values adjusted by the color conversion model, so as to achieve the effect of adjusting the tone of the image.
- the electronic device 100 can provide multiple video style templates, one video style template corresponds to one color conversion model, and different video style templates can bring different display effects to the preview image.
- these video style templates can be associated with the theme of the movie, and the tone adjustment effect brought by the video style template to the preview image can be close to or the same as the tone in the movie, creating an atmosphere for the user to shoot a movie.
- the electronic device 100 can determine a video style template among multiple video style templates according to the current preview video image, and the determined video style template can be displayed on the interface, so that the user can understand Currently determined video style templates, for example, a plurality of video style templates including "A" movie style template, "B" movie style template and "C” movie style template, the corresponding LUTs of different movie style templates can be based on the corresponding Generated by the movie color matching style, the color conversion of the LUT has the style characteristics of the corresponding movie. Film styles can be pre-extracted to produce LUTs suitable for mobile electronics. Turning on the LUT function will change the color tone of the preview video screen. As shown in FIG. 5 , the electronic device 100 determines and displays the "A" movie style template.
- the electronic device 100 may select a video style template according to the user's sliding operation. Specifically, when the electronic device 100 detects the user operation of enabling the LUT function and displays the LUT preview window, the electronic device 100 can select the first video style template located in the LUT preview window by default as the video style template selected by the electronic device 100. template. Afterwards, the electronic device 100 can detect the left and right sliding operation of the user acting on the LUT preview window, and move the position of each video style template in the LUT preview window. The first video style template displayed in the preview window is used as the video style template selected by the electronic device 100 .
- the electronic device 100 in addition to using the video style template to change the display effect of the preview image, can also detect a user operation to start recording a video after adding the video style template, and in response to the operation, the electronic device 100 starts recording Video, so as to obtain the video after adjusting the display effect using the video style template.
- the electronic device 100 can also detect the user operation of taking a photo. In response to this operation, the electronic device 100 saves the preview image with the video style template added in the preview box as a picture, so as to obtain the user's operation of using the video.
- the style template adjusts the image after the display effect.
- HDR10 is a high-dynamic range image (High-Dynamic Range, HDR). Compared with ordinary images, HDR can provide more dynamic range and image details, and can better Reflecting the visual effects in the real environment, 10 in HDR10 is 10 bits, and HDR10 can record video with a high dynamic range of 10 bits.
- the electronic device 100 may detect the user's touch operation on the professional mode option, and enter the professional mode.
- the functional options that can be included in the user interface are, for example: LOG option, flashlight option, LUT option, and setting option.
- the user interface also includes parameter adjustment options, such as: measurement Light M option, ISO option, shutter S option, exposure compensation EV option, focus mode AF option and white balance WB option.
- the electronic device 100 may turn on the professional mode by default after starting the camera application.
- the electronic device 100 can also enable the professional mode in other ways, for example, the electronic device 100 can also enable the professional mode according to the user's voice command, which is not limited in this embodiment of the present application.
- the electronic device 100 may detect a user operation on the LOG option by the user, and in response to the operation, the electronic device 100 starts the LOG function.
- the LOG function can apply the logarithmic function to the exposure curve to preserve the details of the highlights and shadows in the image captured by the camera to the maximum extent, so that the saturation of the final preview image is lower.
- the video recorded with LOG function is called LOG video.
- the electronic device 100 can not only record a video with a video style template added through the professional mode, but also add a video style template to the video after recording a video without a video style template, or record a LOG video after enabling the LOG function. Then add a video style template for the LOG video. In this way, the electronic device 100 can not only adjust the display effect of the picture before recording the video, but also adjust the display effect of the recorded video after the video recording is completed, which increases the flexibility and freedom of image adjustment.
- the embodiment of the present application also provides a video processing device, including: a video acquisition module, configured to acquire a video captured by a camera in the first zoom mode or the second zoom mode, the video includes alternating first exposure frame video images and The second exposure frame video image, the exposure time of the first exposure frame video image is greater than the exposure time of the second exposure frame video image; the super-resolution algorithm module is used to perform super-supervision on the first exposure frame video image in the first zoom mode Sub-algorithm processing, super-resolution algorithm processing is used to improve resolution; fusion module, used in the first zoom mode, for the first exposure frame video image processed by the super-resolution algorithm and the second exposure without super-resolution algorithm processing Frames of video images are fused to obtain a fused video, the first exposure frame video image has the first weight; in the second zoom mode, the first exposure frame video image and the second exposure frame video image are fused, the first exposure frame video image has the first weight; The frame video image has a second weight, and the fused video is obtained, and the first weight is
- each module of the video processing device is only a division of logical functions, and may be fully or partially integrated into one physical entity or physically separated during actual implementation.
- these modules can all be implemented in the form of software called by the processing element; they can also be implemented in the form of hardware; some modules can also be implemented in the form of software called by the processing element, and some modules can be implemented in the form of hardware.
- any one of the video acquisition module, the super-resolution algorithm module and the fusion module can be a separate processing element, and can also be integrated in a video processing device, such as being integrated in a certain chip of the video processing device.
- each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or an instruction in the form of software.
- these modules of the video acquisition module, the super-resolution algorithm module and the fusion module may be one or more integrated circuits configured to implement the above method, for example: one or more specific integrated circuits (Application Specific Integrated Circuit, ASIC), or , one or more microprocessors (digital signal processor, DSP), or, one or more field programmable gate arrays (Field Programmable Gate Array, FPGA), etc.
- ASIC Application Specific Integrated Circuit
- DSP digital signal processor
- FPGA Field Programmable Gate Array
- the processing element may be a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU) or other processors that can call programs.
- these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).
- SOC system-on-a-chip
- An embodiment of the present application further provides a video processing device, including: a processor and a memory, the memory is used to store at least one instruction, and when the instruction is loaded and executed by the processor, the video processing method in any of the foregoing embodiments is implemented.
- the video processing apparatus may apply the above-mentioned video processing method, and the specific process and principle will not be repeated here.
- the number of processors may be one or more, and the processors and memory may be connected through a bus or in other ways.
- the memory can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the video processing device in the embodiment of the present application.
- the processor executes various functional applications and data processing by running non-transitory software programs, instructions and modules stored in the memory, that is, implements the method in any of the above method embodiments.
- the memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function; and necessary data and the like.
- the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage devices.
- an embodiment of the present application further provides an electronic device, including: a camera 193 and the above-mentioned video processing device, where the video processing device includes a processor 110 .
- the electronic device may be any product or component with a video shooting function such as a mobile phone, a TV, a tablet computer, a watch, a bracelet, and the like.
- An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when running on a computer, the computer is made to execute the video processing method in any of the foregoing embodiments.
- all or part of them may be implemented by software, hardware, firmware or any combination thereof.
- software When implemented using software, it may be implemented in whole or in part in the form of a computer program product.
- the computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the present application will be generated in whole or in part.
- the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
- the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server, or data center by wired (eg, coaxial cable, optical fiber, DSL) or wireless (eg, infrared, wireless, microwave, etc.) means.
- the computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
- the available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, a Solid State Disk).
- "at least one” means one or more, and “multiple” means two or more.
- “And/or” describes the association relationship of associated objects, indicating that there may be three kinds of relationships, for example, A and/or B may indicate that A exists alone, A and B exist simultaneously, or B exists alone. Among them, A and B can be singular or plural.
- the character “/” generally indicates that the contextual objects are an “or” relationship.
- “At least one of the following” and similar expressions refer to any combination of these items, including any combination of single items or plural items.
- At least one of a, b, and c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, and c may be single or multiple.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Studio Devices (AREA)
Abstract
Description
Claims (10)
- 一种视频处理方法,其特征在于,包括:在第一变焦模式或第二变焦模式下,获取通过摄像头拍摄的视频,所述视频包括交替的第一曝光帧视频图像和第二曝光帧视频图像,所述第一曝光帧视频图像的曝光时间大于所述第二曝光帧视频图像的曝光时间;在所述第一变焦模式下,对所述第一曝光帧视频图像进行超分算法处理,所述超分算法处理用于提高分辨率;在所述第一变焦模式下,对经过所述超分算法处理的第一曝光帧视频图像和未经所述超分算法处理的第二曝光帧视频图像进行融合,得到融合后的视频,所述第一曝光帧视频图像具有第一权重;在所述第二变焦模式下,对所述第一曝光帧视频图像和所述第二曝光帧视频图像进行融合,所述第一曝光帧视频图像具有第二权重,得到融合后的视频,所述第一权重大于所述第二权重。
- 根据权利要求1所述的视频处理方法,其特征在于,还包括:若当前使用的摄像头为第一摄像头,且拍摄缩放倍数属于第一缩放范围,且当前拍摄画面的亮度大于第一亮度阈值,则进入所述第一变焦模式;若当前使用的摄像头为所述第一摄像头,且拍摄缩放倍数属于第二缩放范围,所述第二缩放范围小于所述第一缩放范围,则进入所述第二变焦模式;若当前使用的摄像头为所述第一摄像头,且拍摄缩放倍数属于所述第一缩放范围,且当前拍摄画面的亮度不大于所述第一亮度阈值,则进入所述第二变焦模式。
- 根据权利要求2所述的视频处理方法,其特征在于,还包括:若当前使用的摄像头为第二摄像头,且拍摄缩放倍数属于第三缩放范围,且摄像头ISO属于第一ISO范围,所述第三缩放范围小于所述第二缩放范围,所述第二摄像头的焦距小于所述第一摄像头的焦距,则进入所述第一变焦模式;若当前使用的摄像头为所述第二摄像头,且拍摄缩放倍数属于第三缩放范围,且摄像头ISO属于第二ISO范围,且当前拍摄画面的亮度大于第二亮度阈值,所述第二ISO范围大于所述第一ISO范围,则进入所述第二变焦模式;若当前使用的摄像头为所述第二摄像头,且摄像头的缩放倍数属于第四缩放范围,所述第四缩放范围小于所述第三缩放范围,且当前拍摄画面的亮度大于第三亮度阈值,则进入所述第二变焦模式。
- 根据权利要求3所述的视频处理方法,其特征在于,还包括:若当前使用的摄像头为所述第二摄像头,且拍摄缩放倍数属于所述第二缩放范围,且拍摄画面的亮度不大于第四亮度阈值,则进入所述第二变焦模式;若当前使用的摄像头为所述第二摄像头,且拍摄缩放倍数属于所述第二缩放范围,且拍摄距离小于距离阈值,则进入所述第二变焦模式;若当前使用的摄像头为所述第二摄像头,且拍摄缩放倍数属于所述第一缩放范围,且拍摄画面的亮度不大于所述第一亮度阈值,则进入所述第二变焦模式;若当前使用的摄像头为所述第二摄像头,且拍摄缩放倍数属于所述第一缩放范围,且拍摄距离小于距离阈值,则进入所述第一变焦模式。
- 根据权利要求1所述的视频处理方法,其特征在于,还包括:在所述第一变焦模式下,通过所述摄像头当前的感光度ISO所对应的对数LOG曲线对所述融合后的视频行处理,得到LOG视频;基于颜色查找表LUT对所述LOG视频进行处理,得到经过LUT处理后的视频。
- 根据权利要求1所述的视频处理方法,其特征在于,还包括:所述对所述第一曝光帧视频图像进行超分算法处理包括:获取所述第一曝光帧视频图像对应的统计信息;将所述统计信息以及所述第一曝光帧视频图像的RAW图像作为输入进行超分算法处理,得到处理后的第一曝光帧视频图像的RAW图像。
- 根据权利要求5所述的视频处理方法,其特征在于,在第一视频处理流程中执行所述通过所述摄像头当前的感光度ISO所对应的对数LOG曲线对所述融合后的视频行处理,得到LOG视频的过程、以及所述基于颜色查找表LUT对所述LOG视频进行处理,得到经过LUT处理后的视频的过程;所述视频处理方法还包括第二视频处理流程,所述第二视频处理流程包括:通过所述摄像头当前的感光度ISO所对应的对数LOG曲线对所述融合后的视频行处理,得到LOG视频;基于查找表LUT对所述LOG视频进行处理,得到经过LUT处理后的视频;所述视频处理方法还包括:将所述第一视频处理流程中经过LUT处理后的视频进行保存;将所述第二视频处理流程中经过LUT处理后的视频进行预览。
- 一种视频处理装置,其特征在于,包括:处理器和存储器,所述存储器用于存储至少一条指令,所述指令由所述处理器加载并执行时以实现如权利要求1至7中任意一项所述的视频处理方法。
- 一种电子设备,其特征在于,包括:摄像头;如权利要求8所述的视频处理装置。
- 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质中存储有计算机程序,当其在计算机上运行时,使得计算机执行如权利要求1至7中任意一项所述的视频处理方法。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP22855030.7A EP4287604B1 (en) | 2021-08-12 | 2022-05-24 | Video processing method and apparatus, electronic device, and storage medium |
| US18/548,465 US12328507B2 (en) | 2021-08-12 | 2022-05-24 | Video processing method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110926921.0A CN115706870B (zh) | 2021-08-12 | 2021-08-12 | 视频处理方法、装置、电子设备和存储介质 |
| CN202110926921.0 | 2021-08-12 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023016044A1 true WO2023016044A1 (zh) | 2023-02-16 |
Family
ID=85181024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/094782 Ceased WO2023016044A1 (zh) | 2021-08-12 | 2022-05-24 | 视频处理方法、装置、电子设备和存储介质 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US12328507B2 (zh) |
| EP (1) | EP4287604B1 (zh) |
| CN (1) | CN115706870B (zh) |
| WO (1) | WO2023016044A1 (zh) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12489966B2 (en) * | 2023-04-21 | 2025-12-02 | Qualcomm Incorporated | Method and apparatus for image capturing |
| CN117560574B (zh) * | 2024-01-10 | 2024-06-18 | 荣耀终端有限公司 | 一种拍摄方法、电子设备和可读存储介质 |
| CN119963723B (zh) * | 2024-12-25 | 2025-11-04 | 网易(杭州)网络有限公司 | 模型处理方法、装置、存储介质和电子设备 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251365A (zh) * | 2016-07-22 | 2016-12-21 | 北京邮电大学 | 多曝光视频融合方法及装置 |
| CN106408518A (zh) * | 2015-07-30 | 2017-02-15 | 展讯通信(上海)有限公司 | 图像融合方法、装置及终端设备 |
| US20180070018A1 (en) * | 2016-09-07 | 2018-03-08 | Multimedia Image Solution Limited | Method of utilizing wide-angle image capturing element and long-focus image capturing element for achieving clear and precise optical zooming mechanism |
| CN110087003A (zh) * | 2019-04-30 | 2019-08-02 | 深圳市华星光电技术有限公司 | 多曝光图像融合方法 |
| CN110619593A (zh) * | 2019-07-30 | 2019-12-27 | 西安电子科技大学 | 一种基于动态场景的双曝光视频成像系统 |
| CN111510698A (zh) * | 2020-04-23 | 2020-08-07 | 惠州Tcl移动通信有限公司 | 图像处理方法、装置、存储介质及移动终端 |
| CN111917950A (zh) * | 2020-06-30 | 2020-11-10 | 北京迈格威科技有限公司 | 图像处理方法、装置、电子设备及存储介质 |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100056279A (ko) * | 2008-11-19 | 2010-05-27 | 삼성전자주식회사 | 디지털 영상 처리장치 및 그 제어방법 |
| US8861893B2 (en) * | 2011-09-27 | 2014-10-14 | The Boeing Company | Enhancing video using super-resolution |
| CN103918251B (zh) | 2011-11-08 | 2016-03-02 | 富士胶片株式会社 | 摄像装置及其控制方法 |
| JP5950678B2 (ja) | 2012-04-27 | 2016-07-13 | キヤノン株式会社 | 撮像装置、制御方法、及びプログラム |
| US9342871B2 (en) | 2014-05-30 | 2016-05-17 | Apple Inc. | Scene motion correction in fused image systems |
| CN106791377B (zh) | 2016-11-29 | 2019-09-27 | Oppo广东移动通信有限公司 | 控制方法、控制装置及电子装置 |
| CN110121882B (zh) * | 2017-10-13 | 2020-09-08 | 华为技术有限公司 | 一种图像处理方法及装置 |
| CN111418201B (zh) * | 2018-03-27 | 2021-10-15 | 华为技术有限公司 | 一种拍摄方法及设备 |
| CN109005342A (zh) * | 2018-08-06 | 2018-12-14 | Oppo广东移动通信有限公司 | 全景拍摄方法、装置和成像设备 |
| US11107205B2 (en) * | 2019-02-18 | 2021-08-31 | Samsung Electronics Co., Ltd. | Techniques for convolutional neural network-based multi-exposure fusion of multiple image frames and for deblurring multiple image frames |
| US11062436B2 (en) * | 2019-05-10 | 2021-07-13 | Samsung Electronics Co., Ltd. | Techniques for combining image frames captured using different exposure settings into blended images |
| CN110445988B (zh) * | 2019-08-05 | 2021-06-25 | Oppo广东移动通信有限公司 | 图像处理方法、装置、存储介质及电子设备 |
| KR102680342B1 (ko) | 2019-09-23 | 2024-07-03 | 삼성전자주식회사 | 복수의 이미지 센서들에 의해 획득되는 이미지 데이터에 기초하여 비디오 hdr 처리를 수행하기 위한 전자 장치 |
| US11516391B2 (en) * | 2020-06-18 | 2022-11-29 | Qualcomm Incorporated | Multiple camera system for wide angle imaging |
| US11190689B1 (en) * | 2020-07-29 | 2021-11-30 | Google Llc | Multi-camera video stabilization |
| US11671715B2 (en) * | 2021-01-14 | 2023-06-06 | Qualcomm Incorporated | High dynamic range technique selection for image processing |
| US12250465B2 (en) * | 2021-07-29 | 2025-03-11 | Qualcomm Incorporated | Systems, methods, and devices for processing image data from multiple image sensors |
| US11924563B2 (en) * | 2021-12-22 | 2024-03-05 | Qualcomm Incorporated | High dynamic range (HDR) photography with in-sensor zoom |
-
2021
- 2021-08-12 CN CN202110926921.0A patent/CN115706870B/zh active Active
-
2022
- 2022-05-24 EP EP22855030.7A patent/EP4287604B1/en active Active
- 2022-05-24 WO PCT/CN2022/094782 patent/WO2023016044A1/zh not_active Ceased
- 2022-05-24 US US18/548,465 patent/US12328507B2/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408518A (zh) * | 2015-07-30 | 2017-02-15 | 展讯通信(上海)有限公司 | 图像融合方法、装置及终端设备 |
| CN106251365A (zh) * | 2016-07-22 | 2016-12-21 | 北京邮电大学 | 多曝光视频融合方法及装置 |
| US20180070018A1 (en) * | 2016-09-07 | 2018-03-08 | Multimedia Image Solution Limited | Method of utilizing wide-angle image capturing element and long-focus image capturing element for achieving clear and precise optical zooming mechanism |
| CN110087003A (zh) * | 2019-04-30 | 2019-08-02 | 深圳市华星光电技术有限公司 | 多曝光图像融合方法 |
| CN110619593A (zh) * | 2019-07-30 | 2019-12-27 | 西安电子科技大学 | 一种基于动态场景的双曝光视频成像系统 |
| CN111510698A (zh) * | 2020-04-23 | 2020-08-07 | 惠州Tcl移动通信有限公司 | 图像处理方法、装置、存储介质及移动终端 |
| CN111917950A (zh) * | 2020-06-30 | 2020-11-10 | 北京迈格威科技有限公司 | 图像处理方法、装置、电子设备及存储介质 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP4287604A4 |
Also Published As
| Publication number | Publication date |
|---|---|
| US12328507B2 (en) | 2025-06-10 |
| EP4287604A1 (en) | 2023-12-06 |
| US20240137650A1 (en) | 2024-04-25 |
| CN115706870A (zh) | 2023-02-17 |
| EP4287604B1 (en) | 2025-07-09 |
| EP4287604A4 (en) | 2024-08-28 |
| CN115706870B (zh) | 2023-12-26 |
| US20240236492A9 (en) | 2024-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113810642B (zh) | 视频处理方法、装置、电子设备和存储介质 | |
| CN113810641B (zh) | 视频处理方法、装置、电子设备和存储介质 | |
| CN115242992B (zh) | 视频处理方法、装置、电子设备和存储介质 | |
| CN113824914B (zh) | 视频处理方法、装置、电子设备和存储介质 | |
| CN114449199B (zh) | 视频处理方法、装置、电子设备和存储介质 | |
| EP4287604B1 (en) | Video processing method and apparatus, electronic device, and storage medium | |
| US12294787B2 (en) | Video processing method and apparatus, electronic device, and storage medium | |
| EP4262192B1 (en) | Video processing method and apparatus, electronic device, and storage medium | |
| WO2023016042A1 (zh) | 视频处理方法、装置、电子设备和存储介质 | |
| US12425535B2 (en) | Video processing method and apparatus, electronic device, and storage medium | |
| CN115706764B (zh) | 视频处理方法、装置、电子设备和存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WWE | Wipo information: entry into national phase |
Ref document number: 18548465 Country of ref document: US |
|
| ENP | Entry into the national phase |
Ref document number: 2022855030 Country of ref document: EP Effective date: 20230829 |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22855030 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWG | Wipo information: grant in national office |
Ref document number: 18548465 Country of ref document: US |
|
| WWG | Wipo information: grant in national office |
Ref document number: 2022855030 Country of ref document: EP |


