WO2019153920A1 - 一种图像处理的方法以及相关设备 - Google Patents
一种图像处理的方法以及相关设备 Download PDFInfo
- Publication number
- WO2019153920A1 WO2019153920A1 PCT/CN2018/123383 CN2018123383W WO2019153920A1 WO 2019153920 A1 WO2019153920 A1 WO 2019153920A1 CN 2018123383 W CN2018123383 W CN 2018123383W WO 2019153920 A1 WO2019153920 A1 WO 2019153920A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- color
- texture
- information
- brightness
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/10048—Infrared image
-
- 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
Definitions
- the present application relates to the field of images, and in particular, a method for image processing and related devices are designed.
- the camera device can capture clear images, while in low illumination, the captured images are often unclear, so the image sharpness under low illumination has always been the camera device. The problem that needs to be improved.
- the light in the optical imaging system, can be separated according to the wavelength band and the ratio by the light splitting device, and the respective frequency components obtained by the separation are respectively imaged to obtain a visible light image and an infrared light image, wherein the visible light image is a color image, and the infrared image is obtained.
- the light image is an achromatic image.
- the visible image and the infrared light image are image-fused by a preset fusion algorithm, and the obtained image can be merged with the image of each frequency component on the infrared light image to obtain the merged target image.
- the color component of the target image is derived from the light image, and after determining the brightness and texture of the target image, the color component is fused to obtain the target image.
- the infrared light image and the visible light image have different brightness distributions, the reflection coefficients of different materials in visible light and infrared light are different, so the brightness difference between the infrared light image and the visible light image is obvious, especially under low illumination, infrared
- the texture distribution and brightness distribution of the light image and the visible light image are quite different.
- the infrared light image is more clear than the visible light image, and the texture of the infrared light image is richer. Therefore, the texture information under the infrared light image will occupy a larger proportion when merging the image. Therefore, the merged target image will be closer to the image texture under infrared light, and the actual texture difference from the image is large, resulting in more severe distortion.
- the embodiment of the present application provides a method for image processing and related equipment for processing an image acquired by an optical imaging system, and performing contrast, texture, and color processing on the image, especially in a low illumination scene.
- the image texture is sharper and the texture and color are closer to the actual texture and color.
- the first aspect of the present application provides a method for image processing, including:
- Obtaining a visible light image and an infrared light image acquiring first brightness information and second brightness information, wherein the first brightness information is brightness information of the visible light image, and the second brightness information is brightness information of the infrared light image;
- the brightness information is fused with the second brightness information to obtain a contrast fused image;
- the first texture information and the second texture information are obtained, the first texture information is texture information of the visible light image, and the second texture information is the infrared light
- the texture information of the image; the first texture information and the second texture information are merged with the contrast fusion image to obtain a texture fusion image; and the color fusion image is obtained according to the visible light image and the infrared light image;
- the image is fused with the color fused image to obtain a target image.
- the brightness information can reduce the noise in the contrast fused image, and can make the brightness distribution in the contrast fused image more uniform, closer to the brightness distribution under visible light, and then extract the first texture information from the visible light image and extract the first texture information from the infrared light image.
- the second texture information, and then the first texture information, the second texture information and the contrast fusion image are merged to obtain a texture fusion image, which can make the texture in the texture fusion image clearer, and can perform color through the infrared light image and the visible light image.
- Fusion to obtain color fusion image, adding infrared light image as the basis of color fusion image, can reduce color missing, color cast or noise, etc. Finally, the color fusion image and texture fusion image are merged to obtain the target image. Can reduce the target map The noise of the image makes the temperature of the target image clearer, and the brightness distribution is closer to the brightness distribution under visible light.
- the acquiring a color fusion image according to the visible light image and the infrared light image may include:
- Color-aware restoration of the visible light image to obtain a color-aware restored image comprising: performing color reasoning on the infrared light image according to a preset color correspondence relationship to obtain a color inference image; and performing the color-sensing restored image and the color-inferential image Fusion to get the color fusion image.
- the color image can be restored by color perception, and the color under the visible light image can be perceived and restored, and the partially missing color can be restored, because the color component in the infrared light image and the visible light
- the color components have a corresponding relationship, and the infrared light image can be color-inferred according to the preset color pair relationship to obtain a color inference image, and then the color perception restored image and the color inference image are combined to obtain a color fusion image, which can pass color
- the color component in the inference image fills the missing part of the color under the visible light, the partial color part or the noise part, makes the color of the color fusion image more complete, reduces the noise in the color fusion image, and further reduces the color noise in the target image. Improve color loss or color cast.
- the first brightness information and the second brightness information are merged to Obtaining a contrast fusion image, which can include:
- the first brightness information and the second brightness information are calculated by a preset first formula to obtain a target brightness value; the contrast fusion image is obtained by the target brightness value.
- the first brightness information and the second brightness information may be calculated by using a preset first formula, and a manner of obtaining a contrast fusion image is added.
- the merging the first texture information and the second texture information with the contrast fused image to obtain a texture fused image may include:
- the first texture information and the second texture information are calculated by a preset second formula to obtain a target texture pixel value; the target texture pixel value is superimposed into the contrast fusion image to obtain the texture fusion image.
- the first texture information and the second texture information may be calculated by using a preset second formula, and a manner of obtaining a texture fusion image is added.
- the infrared light image is color-inferred according to a preset color correspondence relationship to obtain a color inference image.
- the infrared light image is determined according to a preset color correspondence relationship; the target color is determined according to a preset calculation manner according to a ratio of the color component to obtain the color inference image.
- the specific process of obtaining the color inference image may be to obtain a color image by using a color component in the infrared light image according to a preset color correspondence relationship to obtain a color image, thereby adding a method for obtaining a color inference image.
- the visible light image is subjected to color perception restoration, Obtaining a color-aware restored image can include:
- Inverting the brightness of the visible light image to obtain a brightness inversion image Inverting the brightness of the visible light image to obtain a brightness inversion image; calculating the brightness inversion image according to a fogging algorithm to obtain an enhanced image after brightness and color enhancement; and inverting the enhanced image to obtain This color perception restores the image.
- the brightness of the visible light image may be reversed, and then the inverted visible light image is calculated by a fog-transmission algorithm to obtain an image with enhanced brightness and color, and then the brightness and the color are enhanced.
- the image is then inverted to obtain a color-aware image with enhanced color and brightness.
- the merging the texture fused image and the color fused image to obtain the target image may include:
- the luminance information in the texture fusion image is blended with the color component in the color fusion image to obtain the target image.
- the color information in the texture fusion image and the color component in the color fusion image are determined, and then the luminance information is superimposed with the color component or scaled to obtain the target image, so that the color of the target image can be more complete. It can improve the color cast in the target image, the noise is large, the texture is not clear, and the brightness distribution is greatly different from that under visible light.
- a second aspect of the present application provides an image processing apparatus having a function of realizing a method corresponding to the image processing in the first aspect or the first aspect of the present application described above.
- the functions may be implemented by hardware or by corresponding software implemented by hardware.
- the hardware or software includes one or more modules corresponding to the functions described above.
- the third party of the present application provides a camera device, which may include:
- a lens for acquiring an optical image
- the memory for storing program code
- the processor executing the first aspect or the first application when calling the program code in the memory
- a fourth aspect of the present disclosure provides a terminal device, including:
- a lens for acquiring an optical image
- the memory for storing program code
- the processor executing the first aspect or the first application when calling the program code in the memory
- the fifth aspect of the present application provides a storage medium. It should be noted that the technical solution of the present invention or the part that contributes to the prior art or all or part of the technical solution may be embodied in the form of a software product.
- the computer software product is stored in a storage medium for storing computer software instructions for use in the above apparatus, comprising programs for performing the first aspect described above.
- the storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes.
- a sixth aspect of the embodiments of the present application provides a computer program product comprising instructions, which when executed on a computer, cause the computer to perform the method as described in the first aspect of the present application or any of the alternative embodiments of the first aspect.
- a seventh aspect of the present application provides a chip system including a processor for supporting an image processing apparatus to implement the functions involved in the above first aspect, such as transmitting or processing data involved in the above method and/or information.
- the chip system further includes a memory for storing program instructions and data necessary in the method of image processing.
- the chip system can be composed of chips, and can also include chips and other discrete devices.
- the embodiments of the present application have the following advantages:
- the contrast fusion image after the contrast enhancement is obtained by using the brightness information of the light image and the infrared light image, and then passing through the visible light image and the infrared when performing texture fusion
- the texture information of the light image is texture-fused to obtain a texture-fused image with a clearer texture, and then the color fusion image is acquired through the infrared light image and the visible light image.
- the reference embodiment of the present application adds the reference visible light image and the infrared light image.
- the contrast is texture-fused, so that the texture of the texture is more clear, and the brightness and texture of the target image are closer to the brightness and texture under actual visible light, reducing the distortion of the image.
- FIG. 1 is a frame diagram of a method for image processing in an embodiment of the present application
- FIG. 2 is a schematic diagram of an image synthesized in a conventional scheme
- FIG. 3 is a schematic diagram of an embodiment of a method for image processing in an embodiment of the present application.
- FIG. 4 is a schematic diagram of another embodiment of a method for image processing in an embodiment of the present application.
- FIG. 5 is a schematic diagram of another embodiment of a method for image processing in an embodiment of the present application.
- FIG. 6 is a schematic diagram of an embodiment of an image processing apparatus according to an embodiment of the present application.
- FIG. 7 is a schematic diagram of an embodiment of an image pickup apparatus according to an embodiment of the present application.
- the embodiment of the present application provides a method for image processing and related equipment for processing an image acquired by an optical imaging system, and performing contrast, texture, and color processing on the image, especially in a low illumination scene.
- the image texture is sharper and the texture and color are closer to the actual texture and color.
- IR-CUT Filter filters the infrared light in the surrounding environment of the monitoring device, making the infrared light in the environment ineffective.
- the use of the ground reduces the overall amount of light passing through the obtained image.
- the visible light image and the infrared light image are directly fused by the fusion algorithm, so that the frequency of the noise and the frequency range of the image detail are small, so the synthesized image cannot distinguish between noise and image details, resulting in image noise after synthesis.
- the embodiment of the present application provides a method for image processing.
- the low illumination scene described in the embodiment of the present application is a scene with illumination below a threshold
- the threshold for low illumination may be adjusted according to characteristics of devices in the actual optical imaging system, including sensors or optical splitters, for example, If the characteristics of the device are good, the threshold can be lowered, and if the characteristics of the device are low, the threshold can be increased.
- the framework of the image processing method in the embodiment of the present application is as shown in FIG. 1 , wherein the visible light image and the infrared light image are acquired by the optical imaging system, and the optical imaging system may be a camera of the monitoring device, or may be a terminal device or The camera of the camera then combines the visible light image with the infrared light image to obtain a target image, and respectively combines the brightness information, the texture information and the color information of the light image with the infrared light image to obtain a clear target image. And the texture and color of the target image can be made closer to the actual image color.
- the image processing method provided by the embodiment of the present application can make the target image closer to the actual texture and color.
- the image obtained in the existing scheme is as shown in FIG. 2, wherein in the case of low illumination, due to the existing scheme In the image fusion, the texture of the infrared light image is clearer than the brightness and texture of the visible light image. Therefore, the brightness of the infrared light image is larger than the brightness of the visible light image, resulting in the brightness of the merged image and the brightness under the actual visible light.
- the difference from the texture is large. For example, the brightness of the synthesized "tree" in the image of Fig. 2 is too bright, and the difference between the brightness of the "tree" under actual visible light is large.
- the embodiment of the present application obtains a clearer texture fusion image by separately acquiring luminance information and texture information from the visible light image and the infrared light image, and obtains a color fusion image by using the color information of the visible light image and the infrared light image and the above texture.
- the fused image is combined with the target image to enhance the color of the image.
- FIG. 3 including:
- the visible light image and the infrared light image can be obtained by an optical imaging system.
- the visible light image and the infrared light image can be obtained by a camera of a monitoring device, or can be obtained by a single camera or a plurality of cameras of the mobile phone.
- the first brightness information is brightness information in the visible light image
- the second brightness information is brightness information in the infrared light image
- the first brightness information may include brightness values of respective pixels in the visible light image
- the second brightness information may include brightness values of respective pixels in the infrared light image.
- the first brightness information is merged with the second brightness information to obtain a contrast fusion image.
- the specific fusion mode may be that the brightness value in the first brightness information is proportional to the brightness value in the second brightness information.
- the brightness value and the infrared light image in the visible light image can be calculated according to a preset formula.
- the ratio of the brightness value for example, is calculated to be 320 nits.
- the texture of the infrared light image is generally clearer than the texture of the visible light image, so the infrared light image may be added when the image is synthesized. The proportion of the texture.
- the execution sequence of the step 302 and the step 304 is not limited, and the step 302 may be performed first, or the step 304 may be performed first, which is not limited herein.
- the pixel values of all the textures in the visible light image and the infrared light image may be obtained, and the pixel values in the first texture information and the pixel values in the second texture information may be calculated.
- the target texture pixel value is obtained, and then the target texture pixel value is superimposed into the contrast fusion image to obtain a texture fusion image, which can make the texture fusion image texture to be clearer.
- texture details in visible light images are lost more, texture details in infrared light images are more abundant than texture details in visible light images, and infrared light images have less noise than visible light images, so
- the proportion of richer texture information in the infrared light image is increased, so that the texture fused image has a clearer texture and less noise.
- the execution sequence of the step 302 and the step 305 is not limited, and the step 302 may be performed first, or the step 305 may be performed first, which is not limited herein.
- the color information is obtained from the visible light image and the infrared light image respectively, and the visible light image can be restored by color perception to obtain the color information of the visible light image, and the infrared light image is subjected to color reasoning learning according to the preset color correspondence relationship, and the color of the infrared light image is obtained.
- the color information of the visible light image and the color information of the infrared light image are calculated to obtain color components of respective pixel points in the color fusion image to obtain the color fusion image.
- the color particles in the visible light image are large in noise and the color distortion is severe, and the color fusion image obtained by fusing the color information obtained from the infrared light image inference and the color information obtained from the perceived restoration in the visible light image is obtained.
- the color noise is lower and the color is closer to the actual visible light.
- the target image is obtained by fusing the texture fusion image and the color fusion image.
- the luminance component of the target image can be obtained according to the texture fusion image, the color component of the target image is obtained according to the color fusion image, and then the luminance component and the color component are combined to obtain a target image.
- the brightness information is obtained from the visible light image and the infrared light image respectively, and the contrast fusion image is obtained according to the brightness information, and then obtained according to the visible light image and the infrared light image.
- the obtained texture information is fused with the contrast fused image to obtain a texture fused image.
- the texture in the texture fused image is clearer, and the brightness distribution is closer to the brightness distribution of the actual visible light.
- a color fusion image is obtained, and the color missing from the infrared light image can be used to fill the missing color in the visible light image, so that the obtained color fusion image can include the complete color color. Therefore, the texture of the target image obtained by the color fusion image and the texture fusion image is clearer, the brightness distribution is closer to the brightness of the actual illumination, the color in the target image is more complete, and the target image due to the color loss of the visible image is reduced. The color is missing.
- the target image is fused, the luminance and texture information in the infrared light image and the visible light image are respectively fused, and the noise in the synthesized target image can be reduced.
- FIG. 4 Another embodiment of the image processing method in the embodiment of the present application is shown.
- the visible light image 401 and the infrared light image 402 are respectively acquired by the optical imaging system, and then the visible light image 401 passes through the noise reducer 1 to filter out part of the noise in the visible light image, for example, particle noise, and the infrared light image 402 passes through the noise reducer. 2. Filter out part of the noise in the visible image.
- the noise reduction 1 and the noise reducer 2 may be an image signal processing (ISP) noise reducer, and the ISP noise reducer may perform image processing on the infrared light image and the visible light image, including exposure control, white balance control, and lowering. Noise and so on.
- ISP image signal processing
- the image After being processed by the ISP noise reducer 1 and the ISP noise reducer 2, the image is a YUV (luminance signal Y and chrominance signal U, V) format image with accurate color and luminance distribution. That is, the luminance component of the visible light image and the luminance component of the infrared light image can be acquired.
- YUV luminance signal Y and chrominance signal U, V
- the optical imaging system may be a camera or a plurality of cameras. Here, only one camera is taken as an example.
- the lens may include a multi-layer lens, and the image is first collected by the lens, and then passed through.
- the dichroic prism splits, and the sensor 1 generates a visible light image 401, and the sensor 2 generates an infrared light image 402.
- the optical imaging system can also directly generate a visible light image and an infrared light image by a separate imaging device, which can be adjusted according to actual design requirements, which is not limited herein.
- the specific fusion process may be: separately calculating the local contrast in the visible light image and the corresponding local contrast in the infrared light image, and then calculating the local contrast in the visible light image and the corresponding local contrast in the infrared light image according to the preset gradient features.
- the weight of the component may be, for example, taking a corresponding part of the infrared light image and the visible light image as an example.
- the synthesis is performed. Contrast fusion image is more inclined to the local contrast in the infrared light image, that is, the local contrast of the infrared light image and the local contrast of the visible light image are different from the preset gradient features, the weight of the local contrast in the infrared light image Larger, the local contrast in the infrared image will be more used as the local contrast of the contrast fused image.
- the specific contrast fusion process may be an example of a corresponding portion in the visible light image and the infrared light image
- the local portion may be a pixel matrix, for example, a 6*6 pixel matrix.
- the matrix, the second weight matrix may be preset, or may be calculated from actual data.
- the first formula may be Where p is the brightness value of the visible light image, W is the preset fixed matrix, Q is the brightness value of the infrared light image, and ⁇ is the preset coefficient, which can be adjusted according to actual needs, and s i is the brightness value of the pixel point i,
- the texture fused image 406 by the contrast fused image. Extracting first texture information from the visible light image after filtering part of the noise, and extracting second texture information from the infrared light image after filtering the partial noise, and then the first texture information and the pixels included in the second texture information The value is calculated and superimposed, and the first texture information and the pixel value included in the second texture information are superimposed into the contrast fused image to obtain a texture fused image.
- the specific process may be: calculating details in the visible light image and details in the infrared light image, and then calculating an optimal pixel value of each detail texture according to a preset formula, that is, a target pixel value, and then each detail is
- the texture pixel 406 is obtained by superimposing the optimal pixel values of the texture into the contrast fused image.
- the visible image portion may include: acquiring a current visible pixel point x ⁇ ( ⁇ *) , and a value of a pixel point of the non-local average filtered visible light, o, b , and subtracting
- the visible light texture detail ⁇ x ⁇ ( ⁇ *) x ⁇ ( ⁇ *) - x o, b in the visible light image
- the infrared light image portion may include: obtaining the pixel value x n of the non-local average filtered infrared light, and the current infrared light
- the second formula can be: Where ⁇ d is a preset coefficient, which can be adjusted according to actual needs, f j is a preset local weight matrix, and the calculated image pixel values are superimposed into the contrast fusion image to obtain pixel points in the texture fusion image.
- the value is x ⁇ ( ⁇ *) ⁇ x o,b + ⁇ x.
- the noise-reduced visible light image and the noise-reduced infrared light image are color-fused to obtain a color fused image 409.
- the specific process of performing color fusion may be: performing color perception recovery on the visible light image after filtering part of the noise to obtain the color perception restored image 407
- the specific process of performing color perception restoration may be: performing brightness reduction after filtering part of the noise Inverting, obtaining a visible light image after brightness inversion, and then enhancing the brightness and color of the visible light image after the brightness is inverted by a fog-transmission algorithm, and then inverting the inverted image with enhanced brightness and color to obtain brightness Visible light image with color enhancement.
- calculating a proportional relationship of gray values of respective adjacent pixel points in the visible light image after the brightness is inverted and then correcting the gray value of each pixel point by the proportional relationship, and then correcting the gray value of the corrected pixel point.
- the linear enhancement is performed to obtain an enhanced inverted image, and the inverted image is inverted to obtain the visible light image with the brightness and color enhancement.
- the color component in the infrared light image has a corresponding relationship with the color component in the visible light image, and the correspondence relationship may be preset, or RGB (red, green, blue) in the infrared light image may be obtained through a large amount of data and machine learning. Correspondence between the red, blue, and green components and the colors in the visible light image. Therefore, the color component in the infrared light image can be inferred by the correspondence to obtain an image corresponding to the color of the visible light image to obtain a color inference image 408, which can be used to infer the missing color or color cast in the visible light. The part is corrected to get an image with a color closer to the actual lighting.
- the order of obtaining the color perception restored image 407 and the color inference image 408 is not limited in this embodiment, and the color perception restored image 407 may be acquired first, or the color inference image 408 may be acquired first, which may be specifically adjusted according to actual needs. This is not a limitation.
- the color perception restored image 407 can be blended with the color inference image 408 to obtain a color blended image 409.
- the color correction may be determined by referring to the brightness value of the visible light image. If the brightness of the part in the color perception restored image is too low or the noise is too large, the reference proportion of the corresponding part in the color inference image may be improved, ie The color component of the corresponding portion of the color inference image can be used to correct the color of the portion of the brightness that is too low or too noisy to obtain a more complete color fusion image. Therefore, using the visible light image together with the infrared light image to determine the color of the target image can improve the color noise, color distortion, and contamination of the target image in a low illumination scene.
- the order of obtaining the texture fused image 406 and the color fused image 409 is not limited, and the texture fused image 406 may be acquired first, or the color fused image 409 may be acquired first, which may be adjusted according to actual needs, specifically Not limited.
- the texture fused image 406 and the color fused image 409 are obtained, the texture fused image and the color fused image are fused, and the texture details in the texture fused image and the color components in the color fused image are superimposed and combined to obtain the target image 410.
- the brightness information is obtained from the visible light image and the infrared light image respectively, and the contrast fusion image is obtained according to the brightness information, and then according to the texture information acquired from the visible light image and the infrared light image and the contrast fusion image.
- the texture fusion image is obtained by fusion, and the texture in the texture fusion image is clearer, and the brightness distribution is closer to the brightness distribution of the actual visible light.
- a color fusion image is obtained, and the color missing from the infrared light image can be used to fill the missing color in the visible light image, so that the obtained color fusion image can include the complete color color.
- the texture of the target image obtained by the color fusion image and the texture fusion image is clearer, and the brightness distribution is closer to the brightness of the actual illumination, so that the color of the target image is more complete, and the color of the target image caused by the lack of color of the visible image is reduced. Missing.
- the target image is fused, the luminance and texture information in the infrared light image and the visible light image are respectively fused, the noise in the synthesized target image can be reduced, and the color loss or color cast of the synthesized image can be reduced. Improves the problem of color noise, color distortion and contamination of the target image under low illumination.
- FIG. 6 a schematic diagram of an embodiment of an image processing device in the embodiment of the present application may be used. include:
- the brightness information acquiring module 602 is further configured to acquire the first brightness information and the second brightness information, where the first brightness information is brightness information of the visible light image, and the second brightness information is brightness information of the infrared light image;
- the contrast fusion module 603 is configured to fuse the first brightness information with the second brightness information to obtain a contrast fusion image
- the texture information obtaining module 604 is further configured to obtain the first texture information and the second texture information, where the first texture information is texture information of the visible light image, and the second texture information is texture information of the infrared light image.
- a texture fusion module 605 configured to fuse the first texture information, the second texture information, and the contrast fusion image to obtain a texture fusion image
- a color fusion module 606 configured to acquire a color fusion image according to the visible light image and the infrared light image
- the target synthesis module 607 is configured to obtain the target image by fusing the texture fusion image and the color fusion image.
- the color fusion module 606 may include:
- a perceptual complex atom module 6061 configured to perform color-aware restoration on the visible light image to obtain a color-aware restored image
- a color inference sub-module 6062 configured to perform color reasoning on the infrared light image according to a preset color correspondence relationship to obtain a color inference image
- the color blending sub-module 6063 is configured to fuse the color-aware restored image with the color-inferred image to obtain a color-fused image.
- the contrast fusion module 603 is specifically configured to:
- a contrast fused image is obtained from the target luminance value.
- the texture fusion module 605 is specifically configured to:
- the target texture pixel values are superimposed into the contrast fused image to obtain a texture fused image.
- the color inference sub-module 6062 is specifically configured to:
- the target color is determined according to a preset calculation manner according to the ratio of the color components to obtain a color inference image.
- the complex atomic module 6061 is specifically configured to:
- the enhanced image is inverted to obtain a color-aware restored image.
- the target image synthesis module 607 is specifically configured to:
- the luminance information in the texture fused image is fused with the color component in the color fused image to obtain a target image.
- the image processing device when the image processing device is a chip in the terminal, the chip includes: a processing unit and a communication unit, and the processing unit may be, for example, a processor, and the communication unit may be, for example, an input/output. Interface, pin or circuit.
- the processing unit may execute computer execution instructions stored by the storage unit to cause the chip within the terminal to perform the wireless communication method of any of the above aspects.
- the storage unit is a storage unit in the chip, such as a register, a cache, etc., and the storage unit may also be a storage unit located outside the chip in the terminal, such as a read-only memory (read) -only memory, ROM) or other types of static storage devices, random access memory (RAM), etc. that can store static information and instructions.
- the processor mentioned in any of the above may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more for controlling the above.
- CPU central processing unit
- ASIC application-specific integrated circuit
- the integrated circuit of the program execution of the first aspect wireless communication method may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more for controlling the above.
- CPU central processing unit
- ASIC application-specific integrated circuit
- the embodiment of the present invention further provides an image capturing apparatus.
- FIG. 7 for the convenience of description, only parts related to the embodiment of the present invention are shown. For details of the technical disclosure, please refer to the method part of the embodiment of the present invention.
- the camera device can be any terminal device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), a car computer, and the like:
- FIG. 7 is a block diagram showing a part of the structure of an image pickup apparatus according to an embodiment of the present invention.
- the camera device includes: a radio frequency (RF) circuit 710, a memory 720, an input unit 730, a display unit 740, a sensor 750, an audio circuit 760, a lens 770, a processor 780, and a power source 790.
- RF radio frequency
- FIG. 7 does not constitute a limitation of the camera device, and may include more or less components than those illustrated, or some components may be combined, or different component arrangements.
- the RF circuit 710 can be used for transmitting and receiving information or during a call, and receiving and transmitting the signal. Specifically, after receiving the downlink information of the base station, the processor 780 processes the data. In addition, the uplink data is designed to be sent to the base station.
- RF circuit 710 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like.
- LNA Low Noise Amplifier
- RF circuitry 710 can also communicate with the network and other devices via wireless communication. The above wireless communication may use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division). Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), E-mail, Short Messaging Service (SMS), and the like.
- GSM Global System of Mobile communication
- the memory 720 can be used to store software programs and modules, and the processor 780 executes various functional applications and data processing of the camera by running software programs and modules stored in the memory 720.
- the memory 720 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to Data created by the use of the camera (such as audio data, phone book, etc.).
- memory 720 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
- the input unit 730 can be configured to receive input digital or character information and to generate key signal inputs related to user settings and function control of the camera.
- the input unit 730 may include a touch panel 731 and other input devices 732.
- the touch panel 731 also referred to as a touch screen, can collect touch operations on or near the user (such as the user using a finger, a stylus, or the like on the touch panel 731 or near the touch panel 731. Operation), and drive the corresponding connecting device according to a preset program.
- the touch panel 731 can include two parts: a touch detection device and a touch controller.
- the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information.
- the processor 780 is provided and can receive commands from the processor 780 and execute them.
- the touch panel 731 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves.
- the input unit 730 may also include other input devices 732.
- other input devices 732 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.
- the display unit 740 can be used to display information input by the user or information provided to the user and various menus of the camera.
- the display unit 740 can include a display panel 741.
- the display panel 741 can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.
- the touch panel 731 can cover the display panel 741. When the touch panel 731 detects a touch operation on or near the touch panel 731, it transmits to the processor 780 to determine the type of the touch event, and then the processor 780 according to the touch event. The type provides a corresponding visual output on display panel 741.
- the touch panel 731 and the display panel 741 are two independent components to implement the input and input functions of the image pickup apparatus, in some embodiments, the touch panel 731 may be integrated with the display panel 741. The input and output functions of the camera device are realized.
- the camera device may also include at least one type of sensor 750, such as a light sensor, motion sensor, and other sensors.
- the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 741 according to the brightness of the ambient light, and the proximity sensor may close the display panel 741 when the camera moves to the ear / or backlight.
- the accelerometer sensor can detect the magnitude of acceleration in all directions (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity.
- attitude of the camera such as horizontal and vertical screen switching, Related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for the gyroscope, barometer, hygrometer, thermometer, infrared sensor and other sensors that can be configured in the camera device, here No longer.
- An audio circuit 760, a speaker 761, and a microphone 762 can provide an audio interface between the user and the camera.
- the audio circuit 760 can transmit the converted electrical data of the received audio data to the speaker 761 for conversion to the sound signal output by the speaker 761; on the other hand, the microphone 762 converts the collected sound signal into an electrical signal by the audio circuit 760. After receiving, it is converted into audio data, and then processed by the audio data output processor 780, transmitted to the, for example, another camera device via the RF circuit 710, or outputted to the memory 720 for further processing.
- the lens 770 in the camera device can acquire an optical image, including an infrared light image and/or a visible light image, wherein the lens in the camera device can be one or at least two (not shown), depending on the actual Design needs adjustment.
- the processor 780 is a control center of the camera device that connects various portions of the entire camera device using various interfaces and lines, by running or executing software programs and/or modules stored in the memory 720, and recalling data stored in the memory 720.
- the camera performs various functions and processing data to perform overall monitoring of the camera.
- the processor 780 may include one or more processing units; preferably, the processor 780 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application, and the like.
- the modem processor primarily handles wireless communications. It will be appreciated that the above described modem processor may also not be integrated into the processor 780.
- the camera device also includes a power source 790 (such as a battery) that supplies power to various components.
- a power source 790 such as a battery
- the power source can be logically coupled to the processor 780 through a power management system to manage functions such as charging, discharging, and power management through the power management system.
- the camera device may further include a camera, a Bluetooth module, and the like, and details are not described herein again.
- the processor 780 included in the camera device further has the following functions:
- Obtaining a visible light image and an infrared light image acquiring first brightness information and second brightness information, wherein the first brightness information is brightness information of the visible light image, and the second brightness information is brightness information of the infrared light image;
- the brightness information is fused with the second brightness information to obtain a contrast fused image;
- the first texture information and the second texture information are obtained, the first texture information is texture information of the visible light image, and the second texture information is the infrared light
- the texture information of the image; the first texture information and the second texture information are merged with the contrast fusion image to obtain a texture fusion image; and the color fusion image is obtained according to the visible light image and the infrared light image;
- the image is fused with the color fused image to obtain a target image.
- the terminal device provided by the present application may be a mobile phone, a video camera, a monitor or a tablet computer, etc., and the terminal device may further include one or more lenses, which are similar to the camera device shown in FIG. 7 above, and specifically Let me repeat.
- the disclosed system, apparatus, and method may be implemented in other manners.
- the device embodiments described above are merely illustrative.
- the division of the unit is only a logical function division.
- there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
- the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
- the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
- each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
- the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
- a computer readable storage medium A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in connection with Figures 3 through 5 of various embodiments of the present application.
- the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Camera Bodies And Camera Details Or Accessories (AREA)
- Studio Devices (AREA)
Abstract
Description
Claims (15)
- 一种图像处理的方法,其特征在于,包括:获取可见光图像与红外光图像;获取第一亮度信息与第二亮度信息,所述第一亮度信息为所述可见光图像的亮度信息,所述第二亮度信息为所述红外光图像的亮度信息;将所述第一亮度信息与所述第二亮度信息进行融合,以得到对比度融合图像;获取第一纹理信息与第二纹理信息,所述第一纹理信息为所述可见光图像的纹理信息,所述第二纹理信息为所述红外光图像的纹理信息;将所述第一纹理信息、所述第二纹理信息与所述对比度融合图像进行融合,以得到纹理融合图像;获取所述可见光图像与所述红外光图像的色彩融合图像;将所述纹理融合图像与所述色彩融合图像融合,以得到目标图像。
- 根据权利要求1所述的方法,其特征在于,所述根据所述可见光图像与所述红外光图像获取色彩融合图像,包括:对所述可见光图像进行色彩感知复原,以得到色彩感知复原图像;对所述红外光图像按照预置的色彩对应关系进行色彩推理,以得到色彩推理图像;将所述色彩感知复原图像与所述色彩推理图像进行融合,以得到所述色彩融合图像。
- 根据权利要求1或2所述的方法,其特征在于,所述将所述第一亮度信息与所述第二亮度信息进行融合,以得到对比度融合图像,包括:通过预置的第一公式对所述第一亮度信息以及所述第二亮度信息进行计算,以得到目标亮度值;通过所述目标亮度值得到所述对比度融合图像。
- 根据权利要求1-3中任一项所述的方法,其特征在于,所述将所述第一纹理信息、所述第二纹理信息与所述对比度融合图像进行融合,以得到纹理融合图像,包括:通过预置的第二公式对所述第一纹理信息以及所述第二纹理信息进行计算,以得到目标纹理像素值;将所述目标纹理像素值叠加到所述对比度融合图像中,以得到所述纹理融合图像。
- 根据权利要求2所述的方法,其特征在于,所述对所述红外光图像按照预置的色彩对应关系进行色彩推理,以得到色彩推理图像,包括:对所述红外光图像按照预置的色彩对应关系确定色彩分量的比值;根据所述色彩分量的比值按照预置的计算方式确定目标色彩,以得到所述色彩推理图像。
- 根据权利要求2所述的方法,其特征在于,所述对所述可见光图像进行色彩感知复原,以得到色彩感知复原图像,包括:将所述可见光图像的亮度反转,以得到亮度反转图像;根据透雾算法对所述亮度反转图像进行计算,以得到亮度与色彩增强后的增强图像;将所述增强图像进行反转,以得到所述色彩感知复原图像。
- 根据权利要求1-6中任一项所述的方法,其特征在于,所述通过对所述纹理融合图像与所述色彩融合图像进行融合,以得到目标图像,包括:将所述纹理融合图像中的亮度信息与所述色彩融合图像中的色彩分量进行融合,以得到所述目标图像。
- 一种图像处理装置,其特征在于,包括:图像获取模块,用于获取可见光图像与红外光图像;亮度信息获取模块,还用于获取第一亮度信息与第二亮度信息,所述第一亮度信息为所述可见光图像的亮度信息,所述第二亮度信息为所述红外光图像的亮度信息;对比度融合模块,用于将所述第一亮度信息与所述第二亮度信息进行融合,以得到对比度融合图像;纹理信息获取模块,还用于获取第一纹理信息与第二纹理信息,所述第一纹理信息为所述可见光图像的纹理信息,所述第二纹理信息为所述红外光图像的纹理信息;纹理融合模块,用于将所述第一纹理信息、所述第二纹理信息与所述对比度融合图像进行融合,以得到纹理融合图像;色彩融合模块,用于根据所述可见光图像与所述红外光图像获取色彩融合图像;目标图像合成模块,用于通过对所述纹理融合图像与所述色彩融合图像进行融合,以得到目标图像。
- 根据权利要求8所述的图像处理装置,其特征在于,所述色彩融合模块,包括:感知复原子模块,用于对所述可见光图像进行色彩感知复原,以得到色彩感知复原图像;色彩推理子模块,用于对所述红外光图像按照预置的色彩对应关系进行色彩推理,以得到色彩推理图像;色彩融合子模块,用于将所述色彩感知复原图像与所述色彩推理图像进行融合,以得到所述色彩融合图像。
- 根据权利要求8或9所述的图像处理装置,其特征在于,所述对比度融合模块,具体用于:通过预置的第一公式对所述第一亮度信息以及所述第二亮度信息进行计算,以得到目标亮度值;通过所述目标亮度值得到所述对比度融合图像。
- 根据权利要求8-10中任一项所述的图像处理装置,其特征在于,所述纹理融合模块,具体用于:通过预置的第二公式对所述第一纹理信息以及所述第二纹理信息进行计算,以得到目标纹理像素值;将所述目标纹理像素值叠加到所述对比度融合图像中,以得到所述纹理融合图像。
- 根据权利要求9所述的图像处理装置,其特征在于,所述色彩推理子模块,具体用于:对所述红外光图像按照预置的色彩对应关系确定色彩分量的比值;根据所述色彩分量的比值按照预置的计算方式确定目标色彩,以得到所述色彩推理图像。
- 根据权利要求9所述的图像处理装置,其特征在于,所述感知复原子模块,具体用于:将所述可见光图像的亮度反转,以得到亮度反转图像;根据透雾算法对所述亮度反转图像进行计算,以得到亮度与色彩增强后的增强图像;将所述增强图像进行反转,以得到所述色彩感知复原图像。
- 根据权利要求8-13中任一项所述的图像处理装置,其特征在于,所述目标图像合成模块,具体用于:将所述纹理融合图像中的亮度信息与所述色彩融合图像中的色彩分量进行融合,以得到所述目标图像。
- 一种摄像装置,其特征在于,包括:镜头、处理器、存储器、总线以及输入输出接口;所述存储器中存储有程序代码;所述处理器调用所述存储器中的程序代码时执行权利要求1-7中任一项所述方法的步骤。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2020542815A JP6967160B2 (ja) | 2018-02-09 | 2018-12-25 | 画像処理方法および関連デバイス |
| EP18905692.2A EP3734552B1 (en) | 2018-02-09 | 2018-12-25 | Method for image processing and related device |
| US16/943,497 US11250550B2 (en) | 2018-02-09 | 2020-07-30 | Image processing method and related device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810135739.1A CN110136183B (zh) | 2018-02-09 | 2018-02-09 | 一种图像处理的方法、装置以及摄像装置 |
| CN201810135739.1 | 2018-02-09 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US16/943,497 Continuation US11250550B2 (en) | 2018-02-09 | 2020-07-30 | Image processing method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019153920A1 true WO2019153920A1 (zh) | 2019-08-15 |
Family
ID=67547901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/123383 Ceased WO2019153920A1 (zh) | 2018-02-09 | 2018-12-25 | 一种图像处理的方法以及相关设备 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US11250550B2 (zh) |
| EP (1) | EP3734552B1 (zh) |
| JP (1) | JP6967160B2 (zh) |
| CN (1) | CN110136183B (zh) |
| WO (1) | WO2019153920A1 (zh) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613415A (zh) * | 2020-12-25 | 2021-04-06 | 深圳数联天下智能科技有限公司 | 脸部鼻型识别方法、装置、电子设备和介质 |
| WO2021154807A1 (en) * | 2020-01-28 | 2021-08-05 | Gopro, Inc. | Sensor prioritization for composite image capture |
| CN114519808A (zh) * | 2022-02-21 | 2022-05-20 | 烟台艾睿光电科技有限公司 | 图像融合方法、装置及设备、存储介质 |
| CN114830627A (zh) * | 2020-11-09 | 2022-07-29 | 谷歌有限责任公司 | 红外光引导的肖像重照明 |
| JP2022119379A (ja) * | 2021-02-04 | 2022-08-17 | キヤノン株式会社 | 光電変換装置 |
| CN115797697A (zh) * | 2022-12-06 | 2023-03-14 | 北京智芯微电子科技有限公司 | 基于图像的目标检测方法及装置、电子设备及存储介质 |
| CN115953309A (zh) * | 2022-12-20 | 2023-04-11 | 苏州市科远软件技术开发有限公司 | 图像增强模型的训练、图像增强方法及电子设备 |
| CN118968076A (zh) * | 2024-08-05 | 2024-11-15 | 北京积加科技有限公司 | 黑光夜视全彩图像处理方法、装置、电子设备和可读介质 |
Families Citing this family (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108663677A (zh) * | 2018-03-29 | 2018-10-16 | 上海智瞳通科技有限公司 | 一种多传感器深度融合提高目标检测能力的方法 |
| US11410337B2 (en) * | 2018-03-30 | 2022-08-09 | Sony Corporation | Image processing device, image processing method and mobile body |
| CN112767289B (zh) | 2019-10-21 | 2024-05-07 | 浙江宇视科技有限公司 | 图像融合方法、装置、介质及电子设备 |
| CN112712485B (zh) * | 2019-10-24 | 2024-06-04 | 杭州海康威视数字技术股份有限公司 | 一种图像融合方法及装置 |
| CN112785510B (zh) * | 2019-11-11 | 2024-03-05 | 华为技术有限公司 | 图像处理方法和相关产品 |
| CN111161356B (zh) * | 2019-12-17 | 2022-02-15 | 大连理工大学 | 一种基于双层优化的红外和可见光融合方法 |
| CN113014747B (zh) * | 2019-12-18 | 2023-04-28 | 中移物联网有限公司 | 屏下摄像头模组、图像处理方法及终端 |
| CN113711584B (zh) * | 2020-03-20 | 2023-03-03 | 华为技术有限公司 | 一种摄像装置 |
| CN111539902B (zh) * | 2020-04-16 | 2023-03-28 | 烟台艾睿光电科技有限公司 | 一种图像处理方法、系统、设备及计算机可读存储介质 |
| CN113538303B (zh) * | 2020-04-20 | 2023-05-26 | 杭州海康威视数字技术股份有限公司 | 图像融合方法 |
| CN111526366B (zh) * | 2020-04-28 | 2021-08-06 | 深圳市思坦科技有限公司 | 图像处理方法、装置、摄像设备和存储介质 |
| WO2021217428A1 (zh) * | 2020-04-28 | 2021-11-04 | 深圳市思坦科技有限公司 | 图像处理方法、装置、摄像设备和存储介质 |
| CN111667446B (zh) * | 2020-06-01 | 2023-09-01 | 上海富瀚微电子股份有限公司 | 图像处理方法 |
| CN113763295B (zh) * | 2020-06-01 | 2023-08-25 | 杭州海康威视数字技术股份有限公司 | 图像融合方法、确定图像偏移量的方法及装置 |
| CN114143443B (zh) * | 2020-09-04 | 2024-04-05 | 聚晶半导体股份有限公司 | 双传感器摄像系统及其摄像方法 |
| CN112258442A (zh) * | 2020-11-12 | 2021-01-22 | Oppo广东移动通信有限公司 | 图像融合方法、装置、计算机设备和存储介质 |
| CN112396572B (zh) * | 2020-11-18 | 2022-11-01 | 国网浙江省电力有限公司电力科学研究院 | 基于特征增强和高斯金字塔的复合绝缘子双光融合方法 |
| EP4250723B1 (en) * | 2020-12-16 | 2025-05-21 | Huawei Technologies Co., Ltd. | Image generation method and apparatus, and electronic device |
| CN112541903A (zh) * | 2020-12-16 | 2021-03-23 | 深圳市欢太科技有限公司 | 页面比对方法、装置、电子设备及计算机存储介质 |
| CN112767291B (zh) * | 2021-01-04 | 2024-05-28 | 浙江华感科技有限公司 | 可见光图像和红外图像融合方法、设备及可读存储介质 |
| CN112884688B (zh) * | 2021-02-03 | 2024-03-29 | 浙江大华技术股份有限公司 | 一种图像融合方法、装置、设备及介质 |
| CN112767298B (zh) * | 2021-03-16 | 2023-06-13 | 杭州海康威视数字技术股份有限公司 | 一种可见光图像和红外图像的融合方法、装置 |
| CN113344834B (zh) * | 2021-06-02 | 2022-06-03 | 深圳兆日科技股份有限公司 | 图像拼接方法、装置及计算机可读存储介质 |
| CN113421195B (zh) * | 2021-06-08 | 2023-03-21 | 杭州海康威视数字技术股份有限公司 | 一种图像处理方法、装置及设备 |
| CN113298177B (zh) * | 2021-06-11 | 2023-04-28 | 华南理工大学 | 夜间图像着色方法、装置、介质和设备 |
| CN115880192A (zh) * | 2021-09-27 | 2023-03-31 | 北京字跳网络技术有限公司 | 一种特征融合方法、图像去雾方法及装置 |
| CN114387652A (zh) * | 2022-01-12 | 2022-04-22 | 北京百度网讯科技有限公司 | 图像识别方法、识别模型的训练方法、装置和电子设备 |
| CN114565544A (zh) * | 2022-01-18 | 2022-05-31 | 北京旷视科技有限公司 | 一种图像融合方法、设备、产品及介质 |
| CN115457185A (zh) * | 2022-08-15 | 2022-12-09 | 每平每屋(上海)科技有限公司 | 一种生成材质贴图的方法、装置、电子设备和存储设备 |
| CN116091879B (zh) * | 2022-12-21 | 2025-03-11 | 吉林大学 | 一种基于响尾蛇机制不同光照环境的图像融合方法 |
| CN115908518B (zh) * | 2023-01-09 | 2023-05-09 | 四川赛狄信息技术股份公司 | 一种多传感图像融合方法及系统 |
| CN116934642A (zh) * | 2023-07-10 | 2023-10-24 | 天地上海采掘装备科技有限公司 | 图像处理方法、计算机设备、可读介质及视频监控系统 |
| WO2025060610A1 (zh) * | 2023-09-18 | 2025-03-27 | 杭州微影软件有限公司 | 一种图像融合方法、装置、电子设备及存储介质 |
| CN119048365B (zh) * | 2024-08-19 | 2025-04-04 | 山东中微星辰电子科技有限公司 | 基于自适应权重分配的可见光与热成像图像的融合方法 |
| CN119649001A (zh) * | 2024-11-29 | 2025-03-18 | 北京化工大学 | 基于图像处理技术的智能ar眼镜红外热像信息处理方法 |
| CN121032810B (zh) * | 2025-07-22 | 2026-03-06 | 伟龙食品有限公司 | 一种基于图像融合的食品塑封检测方法 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973990A (zh) * | 2014-05-05 | 2014-08-06 | 浙江宇视科技有限公司 | 宽动态融合方法及装置 |
| CN104732507A (zh) * | 2015-04-02 | 2015-06-24 | 西安电子科技大学 | 基于纹理信息重构的不同光照两帧图像融合方法 |
| CN105303598A (zh) * | 2015-10-23 | 2016-02-03 | 浙江工业大学 | 基于纹理传输的多风格视频艺术化处理方法 |
| CN106600572A (zh) * | 2016-12-12 | 2017-04-26 | 长春理工大学 | 一种自适应的低照度可见光图像和红外图像融合方法 |
| CN107346552A (zh) * | 2017-06-23 | 2017-11-14 | 南京信息工程大学 | 基于图像灰度恢复形状技术的纹理力触觉再现方法 |
Family Cites Families (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006072401A (ja) * | 2004-08-31 | 2006-03-16 | Fujitsu Ltd | 画像複合装置および画像複合方法 |
| US7786898B2 (en) * | 2006-05-31 | 2010-08-31 | Mobileye Technologies Ltd. | Fusion of far infrared and visible images in enhanced obstacle detection in automotive applications |
| US8520970B2 (en) * | 2010-04-23 | 2013-08-27 | Flir Systems Ab | Infrared resolution and contrast enhancement with fusion |
| JP2011239259A (ja) * | 2010-05-12 | 2011-11-24 | Sony Corp | 画像処理装置、画像処理方法及びプログラム |
| JP5669513B2 (ja) * | 2010-10-13 | 2015-02-12 | オリンパス株式会社 | 画像処理装置、画像処理プログラム、及び、画像処理方法 |
| KR101858646B1 (ko) * | 2012-12-14 | 2018-05-17 | 한화에어로스페이스 주식회사 | 영상 융합 장치 및 방법 |
| CN103793896B (zh) * | 2014-01-13 | 2017-01-18 | 哈尔滨工程大学 | 一种红外图像与可见光图像的实时融合方法 |
| WO2016206004A1 (zh) * | 2015-06-23 | 2016-12-29 | 华为技术有限公司 | 一种获取深度信息的拍照设备和方法 |
| CN104966108A (zh) * | 2015-07-15 | 2015-10-07 | 武汉大学 | 一种基于梯度传递的可见光与红外图像融合方法 |
| CN105069768B (zh) * | 2015-08-05 | 2017-12-29 | 武汉高德红外股份有限公司 | 一种可见光图像与红外图像融合处理系统及融合方法 |
| CN105513032A (zh) * | 2015-11-27 | 2016-04-20 | 小红象医疗科技有限公司 | 一种红外医学影像与人体切片图像融合的方法 |
| WO2018017904A1 (en) * | 2016-07-21 | 2018-01-25 | Flir Systems Ab | Fused image optimization systems and methods |
| CN106548467B (zh) * | 2016-10-31 | 2019-05-14 | 广州飒特红外股份有限公司 | 红外图像和可见光图像融合的方法及装置 |
| CN106875370B (zh) * | 2017-01-24 | 2020-11-06 | 中国科学院空间应用工程与技术中心 | 一种全色图像和多光谱图像的融合方法及装置 |
| CN107133558B (zh) * | 2017-03-13 | 2020-10-20 | 北京航空航天大学 | 一种基于概率传播的红外行人显著性检测方法 |
| JP6835227B2 (ja) * | 2017-07-13 | 2021-02-24 | 日本電気株式会社 | 画像処理装置、画像処理方法およびコンピュータプログラム |
| CN110363732B (zh) * | 2018-04-11 | 2026-03-17 | 杭州海康威视数字技术股份有限公司 | 一种图像融合方法及其装置 |
| CN110660088B (zh) * | 2018-06-30 | 2023-08-22 | 华为技术有限公司 | 一种图像处理的方法和设备 |
| WO2020051897A1 (zh) * | 2018-09-14 | 2020-03-19 | 浙江宇视科技有限公司 | 图像融合方法、系统、电子设备和计算机可读介质 |
| CN120339355A (zh) * | 2018-09-18 | 2025-07-18 | 松下知识产权经营株式会社 | 信息处理方法、信息处理装置以及计算机程序产品 |
| CN110971889A (zh) * | 2018-09-30 | 2020-04-07 | 华为技术有限公司 | 一种获取深度图像的方法、摄像装置以及终端 |
-
2018
- 2018-02-09 CN CN201810135739.1A patent/CN110136183B/zh active Active
- 2018-12-25 JP JP2020542815A patent/JP6967160B2/ja active Active
- 2018-12-25 WO PCT/CN2018/123383 patent/WO2019153920A1/zh not_active Ceased
- 2018-12-25 EP EP18905692.2A patent/EP3734552B1/en active Active
-
2020
- 2020-07-30 US US16/943,497 patent/US11250550B2/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973990A (zh) * | 2014-05-05 | 2014-08-06 | 浙江宇视科技有限公司 | 宽动态融合方法及装置 |
| CN104732507A (zh) * | 2015-04-02 | 2015-06-24 | 西安电子科技大学 | 基于纹理信息重构的不同光照两帧图像融合方法 |
| CN105303598A (zh) * | 2015-10-23 | 2016-02-03 | 浙江工业大学 | 基于纹理传输的多风格视频艺术化处理方法 |
| CN106600572A (zh) * | 2016-12-12 | 2017-04-26 | 长春理工大学 | 一种自适应的低照度可见光图像和红外图像融合方法 |
| CN107346552A (zh) * | 2017-06-23 | 2017-11-14 | 南京信息工程大学 | 基于图像灰度恢复形状技术的纹理力触觉再现方法 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3734552A4 |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021154807A1 (en) * | 2020-01-28 | 2021-08-05 | Gopro, Inc. | Sensor prioritization for composite image capture |
| US12614246B2 (en) | 2020-01-28 | 2026-04-28 | Gopro, Inc. | Sensor prioritization for composite image capture |
| CN114830627A (zh) * | 2020-11-09 | 2022-07-29 | 谷歌有限责任公司 | 红外光引导的肖像重照明 |
| US12477232B2 (en) | 2020-11-09 | 2025-11-18 | Google Llc | Infrared light-guided portrait relighting |
| CN112613415A (zh) * | 2020-12-25 | 2021-04-06 | 深圳数联天下智能科技有限公司 | 脸部鼻型识别方法、装置、电子设备和介质 |
| JP2022119379A (ja) * | 2021-02-04 | 2022-08-17 | キヤノン株式会社 | 光電変換装置 |
| US12501179B2 (en) | 2021-02-04 | 2025-12-16 | Canon Kabushiki Kaisha | Photoelectric conversion apparatus |
| CN114519808A (zh) * | 2022-02-21 | 2022-05-20 | 烟台艾睿光电科技有限公司 | 图像融合方法、装置及设备、存储介质 |
| CN115797697A (zh) * | 2022-12-06 | 2023-03-14 | 北京智芯微电子科技有限公司 | 基于图像的目标检测方法及装置、电子设备及存储介质 |
| CN115953309A (zh) * | 2022-12-20 | 2023-04-11 | 苏州市科远软件技术开发有限公司 | 图像增强模型的训练、图像增强方法及电子设备 |
| CN118968076A (zh) * | 2024-08-05 | 2024-11-15 | 北京积加科技有限公司 | 黑光夜视全彩图像处理方法、装置、电子设备和可读介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2021513278A (ja) | 2021-05-20 |
| EP3734552A4 (en) | 2021-03-24 |
| US11250550B2 (en) | 2022-02-15 |
| EP3734552A1 (en) | 2020-11-04 |
| CN110136183B (zh) | 2021-05-18 |
| JP6967160B2 (ja) | 2021-11-17 |
| EP3734552B1 (en) | 2025-09-24 |
| US20200357104A1 (en) | 2020-11-12 |
| CN110136183A (zh) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019153920A1 (zh) | 一种图像处理的方法以及相关设备 | |
| TWI696146B (zh) | 影像處理方法、裝置、電腦可讀儲存媒體和行動終端 | |
| US10827140B2 (en) | Photographing method for terminal and terminal | |
| US9536479B2 (en) | Image display device and method | |
| WO2023005870A1 (zh) | 一种图像处理方法及相关设备 | |
| EP3531689A1 (en) | Optical imaging method and apparatus | |
| CN113129222A (zh) | 颜色阴影校正方法、终端设备及计算机可读存储介质 | |
| CN104380727B (zh) | 图像处理装置和图像处理方法 | |
| WO2017088564A1 (zh) | 一种图像处理方法及装置、终端、存储介质 | |
| WO2021093712A1 (zh) | 图像处理方法和相关产品 | |
| CN108200347A (zh) | 一种图像处理方法、终端和计算机可读存储介质 | |
| CN108040240A (zh) | 一种白平衡调整的方法、装置以及移动终端 | |
| CN112243117B (zh) | 图像处理装置、方法及摄像机 | |
| CN108259771A (zh) | 图像处理方法、装置、存储介质和电子设备 | |
| CN115516494A (zh) | 用于生成图像的方法及其电子装置 | |
| CN114125302A (zh) | 图像调整方法及装置 | |
| CN114723613A (zh) | 图像处理方法及装置、电子设备、存储介质 | |
| CN115514876A (zh) | 图像融合方法、电子设备、存储介质及计算机程序产品 | |
| CN119277212B (zh) | 图像处理方法和装置 | |
| CN117391965A (zh) | 图像处理方法、装置、电子设备及芯片 | |
| CN118317203A (zh) | 图像处理方法、装置、电子设备及芯片 | |
| CN118230660A (zh) | 显示处理方法、补偿处理方法、装置、终端和介质 | |
| HK1246948B (zh) | 图像处理方法、装置、计算机可读存储介质和移动终端 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18905692 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2018905692 Country of ref document: EP Effective date: 20200729 Ref document number: 2020542815 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWG | Wipo information: grant in national office |
Ref document number: 2018905692 Country of ref document: EP |