WO2024257816A1 - 画像処理装置、画像処理方法、及び操作機器コントローラ - Google Patents
画像処理装置、画像処理方法、及び操作機器コントローラ Download PDFInfo
- Publication number
- WO2024257816A1 WO2024257816A1 PCT/JP2024/021405 JP2024021405W WO2024257816A1 WO 2024257816 A1 WO2024257816 A1 WO 2024257816A1 JP 2024021405 W JP2024021405 W JP 2024021405W WO 2024257816 A1 WO2024257816 A1 WO 2024257816A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- images
- control unit
- processing device
- detection target
- 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
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
Definitions
- This disclosure relates to an image processing device, an image processing method, and an operation device controller.
- Patent Document 1 An object recognition method using template matching has been known.
- An image processing apparatus comprises: An acquisition unit that acquires a first image; A second image generated based on a training image group including a plurality of detection target images different from the first image, and a control unit that performs a similarity determination between at least a part of the first image, The control unit is The second image can be reproduced; The second image is regenerated based on a training image set that includes a number of unused images that are greater than the used images used to generate the second image.
- An image processing method comprises: acquiring a first image; performing a similarity determination between a second image generated based on a training image group including a plurality of detection target images different from the first image and at least a part of the first image; and regenerating the second image based on a training image set that includes a number of unused images that are greater than the used images used to generate the second image.
- FIG. 1 is a diagram illustrating an example of the configuration of an object operation system including an image processing device according to an embodiment.
- 10 is a diagram for explaining a similarity determination between a representative image and a partial region of the entire image, which is performed by the control unit in FIG. 1 in order to detect the position of a detection target in the entire image.
- 10A and 10B are diagrams for explaining a method of creating a statistical model for determining a pixel value for each pixel of a representative image.
- 13A and 13B are diagrams for explaining a method of creating another statistical model for determining a pixel value for each pixel of a representative image.
- FIG. 13 is a diagram for explaining a method of creating yet another statistical model for determining a pixel value for each pixel of a representative image.
- 4 is a flowchart for explaining a location detection process executed by a control unit in FIG. 1 .
- 4 is a flowchart for explaining a representative image updating subroutine executed by the control unit in FIG. 1 .
- FIG. 1 shows an example of the configuration of a target operation system 11 including an image processing device 10 according to one embodiment.
- the target operation system 11 may include a camera 12, the image processing device 10, an operation device 13, and an operation device controller 20.
- the object operation system 11 performs a specific operation on a detection target 14 such as a manufactured product in a factory, for example.
- the detection target 14 is placed on a tray 15, for example.
- the camera 12 may capture an image of the tray 15 on which the detection target 14 is placed.
- the camera 12 may generate images at a predetermined frame rate, for example, 30 fps, in other words periodically.
- the image processing device 10 may detect the position of the detection target 14 using the image captured by the camera 12.
- the operation device 13 may perform a predetermined task on the detection target 14 at the position detected by the image processing device 10.
- the operation device 13 is, for example, a robot, and may grasp multiple detection targets 14 as a task.
- the operation device controller 20 is configured to include a control unit (second control unit) 21.
- the control unit 21 obtains a similarity judgment in the image processing device 10, which will be described later.
- the control unit 21 is capable of controlling the operation device 13 based on the similarity judgment.
- the operation device controller 20 is, for example, a robot controller.
- the image processing device 10 includes a communication unit (acquisition unit) 16 and a control unit 18.
- the image processing device 10 may further include a memory 17 and an input unit 19.
- the communication unit 16 acquires a first image from the camera 12.
- the first image is also called an overall image.
- the overall image is an image in which the position of the detection target 14 is detected by the image processing device 10.
- the overall image is an image in which the subject to be matched is captured.
- the overall image is also an image in which the background is captured.
- the matching target is an object to be matched with the detection target 14 in the second image, as described below.
- the second image is also called a template image or a representative image. Note that, for example, when the camera 12 captures a specific location, the matching target may not be captured in the overall image, but it does not matter if the matching target is not captured in the overall image. In this case, the image processing device 10 determines that the detection target 14 does not exist in the overall image.
- the image processing device 10 can determine whether the detection target 14 is captured in the overall image.
- the communication unit 16 may be, for example, a communication interface that communicates information and commands with an external device by communication.
- the communication unit 16 may provide the operation device 13 with the position of the detection target 14 in the overall image.
- Memory 17 may include any storage device, such as a RAM (Random Access Memory) and a ROM (Read Only Memory). Memory 17 may store various programs that cause control unit 18 to function, and various information used by control unit 18.
- RAM Random Access Memory
- ROM Read Only Memory
- the memory 17 stores a group of images for template generation.
- the group of images for template generation includes a plurality of detection target images.
- the group of images for template generation may include all of the detection target images stored in the memory 17.
- the group of images for template generation is also referred to as a total image group.
- the detection target images stored in the memory 17 may be deleted and added as appropriate.
- the number of detection target images in the total image group may increase or decrease due to the deletion and addition of detection target images.
- the detection target image is an image of the detection target 14, unlike the first image.
- the multiple detection target images may be acquired in a chronological order, as described below.
- the multiple detection target images may include, for example, at least one original detection target image acquired from the camera 12 and at least one amplified detection target image generated from the original detection target image by an augmentation process.
- the multiple detection target images may include, for example, multiple detection target images acquired under different environments. In this embodiment, an example of a group of images for template generation including multiple detection target images acquired in a chronological order will be described.
- the multiple detection target images may also include multiple processed images in which image processing has been applied to each of the multiple detection target images.
- the image processing may be applied by the control unit 18.
- the image processing may be, for example, a brightness adjustment process that applies to the entire detection target image, for each of the multiple detection target images, the change in pixel value between multiple detection target images that were acquired before and after the detection target image in the template generation image group.
- the image processing may be, for example, a process that adds a disturbance that occurs suddenly to multiple detection target images that are acquired before and after each of the multiple detection target images.
- the group of images for template generation may include a group of training images.
- the group of training images includes a plurality of detection target images that are a portion of all the detection target images included in the group of images for template generation. As described below, the detection target images included in the group of training images are used to generate or regenerate a representative image.
- the group of training images may be selected and extracted as training images from the group of images for template generation each time.
- the input unit 19 may include one or more interfaces that detect user operation input.
- the input unit 19 may include, for example, physical keys, capacitive keys, and a touch screen that is integral with the display device.
- the control unit 18 includes one or more processors and memories.
- the processor may include a general-purpose processor that loads a specific program to execute a specific function, and a dedicated processor specialized for a specific process.
- the dedicated processor may include an application specific integrated circuit (ASIC).
- the processor may include a programmable logic device (PLD).
- the PLD may include a field-programmable gate array (FPGA).
- the control unit 18 may be either a system-on-a-chip (SoC) in which one or more processors work together, or a system in a package (SIP).
- SoC system-on-a-chip
- SIP system in a package
- the control unit 18 performs a similarity judgment between the second image ri, which will be described later, and at least a partial area of the first image wi, with the second image ri being superimposed on the partial area.
- the control unit 18 may determine whether the matching target of the first image wi is the detection target 14 or whether the detection target 14 is captured in the first image wi.
- a second image (representative image) ri which is smaller than the first image (full image) wi, is superimposed on a partial area of the first image (full image) wi.
- the similarity judgment will be described later using a detailed example.
- control unit 18 may detect the location of the detection target 14, for example, in addition to determining whether the matching target is the detection target 14. Specifically, the control unit 18 may detect the location of the detection target 14 in the entire image wi by displacing the representative image ri relative to the entire image wi, thereby displacing an overlapping area that is a part of the entire image wi that overlaps with the representative image ri, and performing a similarity determination at each position.
- control unit 18 may acquire the portion of the region as an unused detection target image. Furthermore, the control unit 18 may include the acquired unused detection target image in the training image group. Specifically, the control unit 18 stores the portion of the region in the entire image wi that is determined to be similar to the representative image ri in the memory 17 so that it is included in the training image group as an unused detection target image, which will be described later. Note that an unused detection target image is also referred to as an unused image, and an unused image that is not used in particular to generate or regenerate the representative image ri is also referred to as a first unused image.
- the control unit 18 regenerates the representative image ri based on the training image group.
- the representative image ri has a size equal to or smaller than the entire image wi.
- the control unit 18 performs the regeneration by replacing the representative image ri stored in the working memory of the control unit 18 or the memory 17 with an image newly created based on the training image group. Note that the regeneration of the representative image ri is also called updating the representative image ri.
- the control unit 18 may store a newly generated image based on the training image group as the first representative image ri.
- the training image group may already contain multiple images of the detection target 14 that have actually been captured as initial detection target images.
- the number of detection target images to be included in the training image group may be determined arbitrarily.
- the number of detection target images to be included in the training image group may be the same as a first number, greater than the first number, or less than the first number, as described below.
- the control unit 18 can regenerate the representative image ri.
- the control unit 18 may be able to regenerate the representative image ri two or more times.
- the control unit 18 may regenerate the representative image ri when the number of unused images included in the training image group reaches a first number.
- the first number may be determined according to the size and generation method of the representative image ri. For example, in a configuration in which the representative image ri is created based on the statistical values of pixel values of multiple detection target images described below, the first number may be determined to be the minimum value at which a significant statistical value can be calculated. Note that the timing of regenerating the representative image ri may be set arbitrarily.
- the control unit 18 may regenerate the representative image ri at predetermined elapsed times, or may regenerate the representative image ri when the accuracy of the similarity judgment drops below a predetermined threshold.
- An unused image is a detection target image that has never been used to generate or regenerate a representative image ri.
- the control unit 18 may recognize an unused image as a used detection target image after using it to regenerate a representative image ri.
- a used detection target image is a detection target image that was used to regenerate a representative image ri before the last time.
- a used detection target image is also referred to as a used image, and a used image that has been used to generate or regenerate a representative image ri is also referred to as a first used image.
- the training image group includes a greater number of first unused images than the number of first used images.
- the control unit 18 uses more first unused images than the first used images in updating the representative image ri.
- the training image group may include a plurality of unused images that have not been used in updating a past representative image ri when updating a new representative image ri. Also, when updating a new representative image ri, the proportion of the plurality of unused images in the training image group may be greater than the proportion of used images that have been used in updating a past second image in the training image group.
- the training image group may include a first used image. Or, the training image group may not include a first used image.
- the training image group does not have to include a first used image that has been used four or more times in the generation and regeneration of the representative image ri.
- the training image group may include more first used images that have been used n-1 times in the generation and regeneration of the representative image ri than first used images that have been used n times in the generation and regeneration of the representative image ri.
- n is any natural number.
- the training image group may include more first used images that have been used two times in the generation and regeneration of the representative image ri than first used images that have been used three times in the generation and regeneration of the representative image ri.
- control unit 18 may delete the first used images in the training image group used to update the immediately preceding representative image ri from the training image group in order of oldest to newest. In other words, the control unit 18 may replace the oldest first used image included in the training image group with a new first unused image.
- control unit 18 may change the ratio of the number of first unused images to the total number of detection target images in the training image group for each regeneration.
- control unit 18 may change the number of detection target images to be included in the training image group for each regeneration.
- control unit 18 may use a number of unused images in regenerating the second image that differs from the number of unused images used in the previous regeneration.
- the control unit 18 may perform the above-mentioned replacement when the number of detection target images included in the training image group is the number of detection target images to be used when updating the next representative image ri, and when a new first unused image is to be included in the training image group.
- the number of detection target images included in the training image group may be different when the representative image ri is generated and when it is regenerated.
- the number of detection target images included in the training image group may be the same as the first number, or may be different.
- the control unit 18 may generate the representative image ri by various methods using the training image group. For example, the control unit 18 may create a statistical model such as a histogram or a mixed Gaussian distribution of pixel values based on pixel values of pixels at corresponding addresses between each detection target image included in the training image group. The control unit 18 may determine the pixel value of each pixel based on the statistical model created for each pixel. The control unit 18 may generate the representative image ri by determining pixel values of addresses of multiple pixels.
- a statistical model such as a histogram or a mixed Gaussian distribution of pixel values based on pixel values of pixels at corresponding addresses between each detection target image included in the training image group.
- the control unit 18 may determine the pixel value of each pixel based on the statistical model created for each pixel.
- the control unit 18 may generate the representative image ri by determining pixel values of addresses of multiple pixels.
- control unit 18 may determine the pixel value that is the most frequent value in the statistical model created for each pixel as the pixel value of that pixel in the representative image ri. Furthermore, the control unit 18 may determine a range in the statistical model for classifying the pixel values of that pixel into multiple classes in order to perform a disturbance judgment in a part of the entire image wi in the similarity judgment described below.
- the multiple classes may include a non-disturbance class, a known disturbance class, and an unknown disturbance class. As shown in FIG. 6, the control unit 18 may recognize a peak including the most frequent value as the non-disturbance class in the statistical model.
- the control unit 18 may recognize a peak other than the non-disturbance class as the known disturbance class.
- the control unit 18 may recognize a range of pixel values other than the non-disturbance class and the known disturbance class as the unknown disturbance class.
- the pixel value ranges that define the non-disturbance class and the known disturbance class may be set to a range of ⁇ 6 ⁇ centered on the mode of each Gaussian distribution in a configuration in which the statistical model is approximated to a Gaussian mixture model. Note that the pixel value ranges that define the non-disturbance class and the known disturbance class can be set arbitrarily within a range that satisfies the desired accuracy.
- the pixels at corresponding addresses may only be pixels located at the same address between the images, as shown in FIG. 3.
- the pixels at corresponding addresses may be multiple pixels included in an area of, for example, 3 ⁇ 3 pixels centered on the same address, as shown in FIG. 4.
- the pixels at corresponding addresses may be multiple pixels in a section including the same address within a section obtained by dividing each image into multiple grids, as shown in FIG. 5.
- the statistics may take into account multiple detection target images, including the multiple processed images described above.
- the control unit 18 performs a similarity judgment by comparing the generated representative image ri with a partial area of the entire image wi. For example, the control unit 18 may perform a similarity judgment by comparing the pixel values of at least a part of all pixels constituting the representative image ri with the pixel values of pixels (pixels with the same address) in the entire image wi that overlap with the representative image ri when the generated representative image ri is superimposed on a part of the entire image wi.
- the control unit 18 may then determine whether or not there is a region in the entire image wi that is similar to the representative image ri by comparing the pixels of the representative image ri with the pixels of the entire image wi that overlap with the representative image ri for each displacement while displacing the overlapping area between the representative image ri and the entire image wi. Note that when the control unit 18 performs a similarity judgment between the entire image wi and the representative image ri, it is not necessary to actually superimpose the entire image wi and the representative image ri, and it is sufficient to obtain the positions of each pixel by arithmetic processing when it is assumed that the entire image wi and the representative image ri overlap.
- the control unit 18 may compare all the pixels constituting the generated representative image ri with all the pixels in a partial area of the entire image wi.
- control unit 18 may select pixels to be used for comparison with the entire image wi as matching pixels from among the multiple pixels constituting the generated representative image ri. For example, the control unit 18 may determine multiple characteristic pixels in the representative image ri as matching pixels. The control unit 18 may select pixels corresponding to feature points such as edges and corners as characteristic pixels. Alternatively, the control unit 18 may select multiple characteristic pixels based on a spatial co-occurrence histogram calculated for the pixel values of multiple pixels arbitrarily selected from the representative image ri. A combination of pixel values that occurs frequently in the spatial co-occurrence histogram means that it occurs frequently in the representative image ri but is not characteristic. Therefore, the control unit 18 may select multiple pixels that correspond to combinations whose frequency exceeds zero and is equal to or less than a feature threshold in the spatial co-occurrence histogram as characteristic pixels.
- the control unit 18 may select matching pixels from all pixels or from multiple characteristic pixels. In the following, a configuration in which selection is made from multiple characteristic pixels is described as an example.
- the control unit 18 may, for example, select multiple stable pixels (hereinafter, also referred to as "stable pixels") as matching pixels from the multiple characteristic pixels. In other words, the control unit 18 may use the stable pixels as matching pixels for comparison.
- the control unit 18 may select stable pixels using at least one detection target image in the training image group. Specifically, the control unit 18 may extract stable pixels with small variations in pixel values by, for example, comparing the pixel values of pixels at the same address in the multiple detection target images with the pixel values of pixels at the same address in the representative image ri, and further by analogy judgment. More specifically, the control unit 18 may select stable pixels based on an inter-image co-occurrence histogram calculated for the multiple detection target images and the representative image ri. A combination of pixel values with a high frequency in the inter-image co-occurrence histogram means that the pixel values are stable with respect to time changes, in other words, the influence of sudden disturbance factors is low.
- the control unit 18 may calculate the stability rate for each pixel of the representative image ri based on multiple inter-image co-occurrence histograms calculated for the multiple detection target images.
- the control unit 18 may select characteristic pixels whose stability rate is equal to or greater than a stability threshold as stable pixels.
- the number of detection target images used to extract stable pixels may be less than the number of detection target images used to generate or update the representative image ri including the stable pixel.
- the stable pixel may be reselected at least once for each similarity judgment between the first image and the second image.
- the period of reselection of stable pixels may be the same as the period of regeneration of the representative image ri, or may be different.
- Reselection of stable pixels means changing the detection target image used to select stable pixels. For reselection of stable pixels, a detection target image that has not been used in the selection or reselection of stable pixels in the past may be used. Note that an unused detection target image is also referred to as an unused image.
- an unused image that has not been used for selection or reselection of stable pixels is also referred to as a second unused image.
- the second unused image may refer to the same one as the first unused image described above.
- the detection target image used to select stable pixels may be selected in the order of acquisition time from the updated training image group.
- the proportion of the second unused images in the training image set for selecting or reselecting stable pixels may be the same as the proportion of the first unused images in the training image set for updating the representative image ri. Or, the proportion of the second unused images in the training image set for selecting or reselecting stable pixels may be different from the proportion of the first unused images in the training image set for updating the representative image ri. More specifically, the proportion of the second unused images in the training image set for selecting or reselecting stable pixels may be lower than the proportion of the first unused images in the training image set for updating the representative image ri. Or, the proportion of the second unused images for selecting or reselecting stable pixels may be higher than the proportion of the first unused images for regenerating the representative image ri.
- the control unit 18 may extract stable pixels directly from the representative image ri. For example, the control unit 18 may calculate the product of the normalized frequency of the spatial co-occurrence histogram calculated as described above and the inverse of the normalized frequency of the inter-image co-occurrence histogram calculated as described above. The control unit 18 may extract a combination of pixels for which the product is equal to or less than a threshold value as a stable pixel.
- the control unit 18 may store the address of the determined group of match pixels in the memory 17.
- the group of match pixels is a plurality of match pixels that are newly selected for the representative image ri stored in the memory 17 based on the updated group of training images.
- the control unit 18 may update the addresses of the group of match pixels by replacing the addresses of the group of match pixels stored in the memory 17 with each address of the newly determined group of match pixels.
- the control unit 18 may store the statistical model for the match pixels in the memory 17 together with the group of addresses of the match pixels.
- the control unit 18 may calculate the similarity by summing up the differences in pixel values between pixels constituting the generated representative image ri and pixels in a partial area of the entire image wi, which have the same address. In a configuration in which matching pixels are selected, the control unit 18 may calculate the similarity by focusing on multiple matching pixels in the representative image ri. The control unit 18 may determine that a partial area of the entire image wi, in which the similarity is equal to or less than a threshold, is an image portion that includes an image similar to the detection target 14. The control unit 18 may determine the position of the image portion as the location of the detection target 14. Note that, when summing up the differences in pixel values, a lower similarity indicates a higher degree of agreement.
- a similarity that increases with a higher degree of agreement may be used, such as a configuration in which the similarity is judged by the cosine similarity of pixel values.
- a partial area of the entire image wi, in which the similarity is equal to or greater than a threshold may be determined to be an image portion that includes an image similar to the detection target 14.
- the control unit 18 may exclude some of the matching pixels from the similarity calculation.
- the excluded pixels may be pixels whose pixel values in a partial area of the entire image wi that has the same address as the matching pixels are classified as a known disturbance class or an unknown disturbance class in the pixel statistical model, as shown in FIG. 6.
- the control unit 18 may perform a similarity judgment using the remaining excluded matching pixels.
- control unit 18 may not need to perform analogical judgment based on similarity if a specific condition is met using a statistical model of pixels created for disturbance judgment.
- a partial area of the entire image wi may be determined to be dissimilar to the representative image ri.
- the specific condition is when, among all the pixels used for comparison in the partial area, there is a large number of pixels having pixel values classified into a known disturbance class and an unknown disturbance class in the corresponding statistical model, or when there is a large number of pixels having pixel values outside a certain range centered on the most frequent pixel value.
- a large number of pixels may mean exceeding a specified ratio to all pixels.
- the number of pixels that satisfy the above-mentioned condition among all pixels may be large when the number of pixels whose pixel values satisfy the above-mentioned condition is equal to or greater than a threshold value.
- the number of pixels that satisfy the above-mentioned condition among all pixels may be large when the ratio of pixels that satisfy the above-mentioned condition to all pixels used for comparison is equal to or greater than a threshold value.
- the control unit 18 when the control unit 18 detects the position of the detection target 14 in the entire image wi, the control unit 18 may include an image portion of a partial area of the entire image wi that corresponds to the position as an unused image in the training image group and store it in the memory 17. Furthermore, when the similarity falls within a first range having a limit value on the matching side, the control unit 18 may include the image portion as an unused image in the training image group.
- the limit value on the matching side is an upper limit value in a configuration in which the higher the similarity, the higher the matching, and is a lower limit value in a configuration in which the lower the similarity, the higher the matching.
- the presence position detection process starts by acquiring one frame of the entire image wi.
- step S100 the control unit 18 reads out the statistical model of the matching pixels in the representative image ri from the memory 17. After reading out, the process proceeds to step S101.
- step S101 the control unit 18 extracts a partial area of the acquired entire image wi, the area being the same size as the detection target image included in the training image group, as an area for similarity judgment. After extraction, the process proceeds to step S102.
- step S102 the control unit 18 compares the pixel values of the same addresses as the match pixels in the partial area extracted in the most recent step S101 with the statistical model of the match pixels. After the comparison, the process proceeds to step S103.
- step S103 the control unit 18 determines whether or not there are many pixels that are recognized as disturbances in the partial region based on the comparison in the most recent step S102. If there are not many pixels that are recognized as disturbances, the process proceeds to step S104. If there are many pixels that are recognized as disturbances, the process proceeds to step S111.
- step S104 the control unit 18 reads from the memory 17 the pixel value of the matching pixel at the same address as the pixel determined to be non-disturbance by the comparison in the most recent step S102. After reading, the process proceeds to step S105.
- step S105 the control unit 18 calculates the similarity between the representative image ri and the partial area based on the pixel values of the matching pixels read out in step S104 and the pixels of the partial area at the same address. After the calculation, the process proceeds to step S106.
- step S106 the control unit 18 determines whether the similarity is equal to or less than the threshold. If it is equal to or less than the threshold, the process proceeds to step S107. If it is not equal to or less than the threshold, the process proceeds to step S111.
- step S107 the control unit 18 determines that the partial area extracted in the previous step S101 is the location of the detection target 14. After this determination, the process proceeds to step S108.
- step S108 the control unit 18 determines whether the similarity calculated in the most recent step S105 is within the first range. If it is within the first range, the process proceeds to step S109. If it is not within the first range, the process proceeds to step S111.
- step S109 the control unit 18 stores the partial area extracted in the most recent step S101 in the memory 17 as an unused image to be included in the training image group. After storage, the process proceeds to step S110.
- step S110 the control unit 18 determines whether the number of unused images included in the training image group has reached the first number. If it has, the process proceeds to step S200. If it has not, the process proceeds to step S111.
- step S200 the control unit 18 updates the representative image ri as described below. After updating, the process proceeds to step S111.
- step S111 the control unit 18 determines whether or not the entire area of the entire image wi has been extracted as a partial area. If the entire area has not been extracted, the process proceeds to step S112. If the entire area has been extracted, the detection process ends.
- step S112 the control unit 18 displaces the partial area extracted in step S101 while maintaining the same size. After the displacement, the process returns to step S101.
- step S201 the control unit 18 reads out the training image group from the memory 17. After reading out, the process proceeds to step S202.
- step S202 the control unit 18 creates a statistical model for each pixel based on the multiple detection target images included in the training image group read out in the most recent step S201. After creation, the process proceeds to step S203.
- step S203 the control unit 18 generates a representative image ri based on the statistical model created in the most recent step S202. After generation, the process proceeds to step S204.
- step S204 the control unit 18 determines matching pixels in the representative image ri generated in the most recent step S203.
- the control unit 18 may use the training image group and the representative image ri to determine the matching pixels. After the determination, the process proceeds to step S205.
- step S205 the control unit 18 replaces the statistical model created in the most recent step S202, the representative image ri generated in the most recent step S203, and the matching pixels determined in the most recent step S204 with the statistical model, the representative image ri, and the matching pixels already stored in the memory 17. After the replacement, the process proceeds to step S206.
- step S206 the control unit 18 converts the status of all detection target images included in step S201 from unused to used. After the conversion, the representative image update subroutine S200 ends, and the process returns to the presence position detection process.
- the image processing device 10 of this embodiment configured as described above includes a communication unit (acquisition unit) 16 that acquires a first image wi, and performs a similarity judgment between a second image ri generated based on a training image group including a plurality of detection target images different from the first image wi and at least a portion of the first image wi, and regenerates the second image based on a training image group including a plurality of unused images that are greater than the used images used to generate the second image ri.
- acquisition unit 16 acquires a first image wi, and performs a similarity judgment between a second image ri generated based on a training image group including a plurality of detection target images different from the first image wi and at least a portion of the first image wi, and regenerates the second image based on a training image group including a plurality of unused images that are greater than the used images used to generate the second image ri.
- the image processing device 10 uses more detection target images acquired at a relatively recent time when updating the second image ri for which a similarity judgment is performed with a portion of the first image wi, and therefore can create a second image ri that better reflects the effects of disturbances that have occurred. Therefore, the image processing device 10 can improve the robustness of detecting the detection target 14 even when disturbances occur.
- the training image group includes used images.
- the image processing device 10 can use detection target images under various circumstances to generate the second image ri. Therefore, the image processing device 10 can reduce the possibility of missing detection of the detection target image from the first image wi.
- the training image group does not include used images.
- the image processing device 10 can reflect the effects of the most recent disturbance in the second image ri. Therefore, the image processing device 10 can further improve the robustness of detecting the detection target 14 from the first image wi in a situation where a disturbance is occurring.
- the image processing device 10 of this embodiment includes a part of the first image wi as an unused image in the training image group when the similarity for similarity judgment is within a first range with a limit value on the matching side. If there are many detection target images that are highly consistent with the second image ri, the possibility of missing detection of an image where a disturbance has occurred with respect to the detection target image increases. In response to such an event, the image processing device 10 having the above-mentioned configuration can reduce the possibility of missing detection by ensuring diversity in the detection target images for updating the second image ri.
- the image processing device 10 of this embodiment when the image processing device 10 of this embodiment includes an unused image in the training image group, it deletes from the training image group the images of the detection target 14 that have been used in the training image group used to update the immediately preceding second image ri, in order of oldest to newest, from the training image group.
- the image processing device 10 can gradually reduce the influence of disturbances that occurred in the past on the second image ri, thereby reducing the possibility of missed detection, while gradually increasing the influence of disturbances that have recently occurred on the second image ri. Therefore, the image processing device 10 can improve the robustness of detecting the detection target 14 while reducing the possibility of missed detection.
- the image processing device 10 of this embodiment regenerates the second image ri based on a training image group that has a different number of images from when the second image ri was generated. Before the start of actual imaging, it is required to reflect the effects of detection target images under various conditions in the second image ri, while after imaging begins, it is required to reflect the effects of variable disturbances that occur in the second image ri. In response to such demands, the image processing device 10 having the above-mentioned configuration can appropriately respond to each purpose before and after imaging begins, since the number of images of the detection target 14 included in the training image group is different.
- the image processing device 10 of this embodiment uses a number of unused images when regenerating the second image ri that differs from the number of unused images used during the previous regeneration.
- the time interval during which any type of disturbance occurs may vary depending on the type of disturbance.
- the image processing device 10 having the above-mentioned configuration can generate an appropriate representative image ri according to the length of time during which the disturbance occurs by changing the number of unused images used.
- the image processing device 10 can further improve the robustness of detecting the detection target 14.
- the image processing device 10 of this embodiment performs similarity judgment by comparing the second image ri with the first image wi, and uses multiple characteristic pixels of the second image ri as objects of comparison with the first image wi.
- the calculation load is high and detection takes a relatively long time.
- the image processing device 10 having the above-mentioned configuration reduces the calculation load while suppressing a decrease in detection accuracy by comparing characteristic pixels, thereby shortening the detection time.
- the image processing device 10 of this embodiment performs similarity judgment by comparing the second image ri with the first image wi, and uses multiple stable pixels in the second image ri as comparison targets, and the multiple stable pixels are selected based on the similarity judgment between the second image ri and at least one detection target image in the training image group. Characteristic pixels in the second image ri may become characteristic due to noise, etc. The use of such pixels for comparison may reduce the accuracy of detection. In response to such events, the image processing device 10 having the above-mentioned configuration can reduce the effects of noise and suppress a decrease in detection accuracy.
- the number of multiple detection target images used to select stable pixels is smaller than the number of detection target images used to generate or regenerate the second image ri.
- the second images ri are assumed to be the minimum number required to reflect the general trend of the situation.
- the stability of pixel values becomes such that disturbances in the most recent detection target image are considered to be noise, and pixels that are actually stable may be determined to be unstable.
- the image processing device 10 having the above-mentioned configuration can appropriately generate the second image ri and determine its stability.
- the period for reselecting stable pixels is different from the period for regenerating the second image ri.
- the pixel where the disturbance occurs is useful for calculating the similarity.
- the time at which the disturbance occurs varies widely and is different from the update period of the second image ri.
- the image processing device 10 having the above-mentioned configuration can respond to a reselection period for stability determination that is different from the period appropriate for regenerating the second image ri by having different periods for reselection and regeneration.
- the period for reselecting stable pixels is the same as the period for regenerating the second image ri.
- the image processing device 10 can reduce the processing load by matching the periods of both.
- the proportion of unused images used to reselect stable pixels is different from the proportion of unused images used to regenerate the second image ri.
- the appropriate proportion of unused images for updating the second image ri and the appropriate proportion of unused images for stability determination may differ.
- the image processing device 10 having the above-described configuration can reflect the general trend of the situation in the second image ri, while more fully reflecting the influence of the most recent detection target image for stability determination.
- the proportion of unused images used to reselect stable pixels is higher than the proportion of unused images used to regenerate the second image ri, and the amount of data in the training image group is small.
- the image processing device 10 can extract stable pixels taking into account disturbances and brightness changes that appear in the most recently acquired first image wi. Therefore, the image processing device 10 can select stable pixels for each lot in a situation where there are disturbances that occur continuously in a short period of time, for example, variations from lot to lot (when one lot is smaller than the number required to regenerate the second image ri). As a result, the image processing device 10 can improve robustness.
- an image processing device includes: An acquisition unit that acquires a first image; A second image generated based on a training image group including a plurality of detection target images different from the first image, and a first control unit that performs a similarity determination between at least a portion of the first image, The first control unit is The second image can be reproduced; Regenerating the second image based on a training image set that includes a number of unused images that are greater than the used images used to generate the second image.
- the first control unit is capable of regenerating the second image two or more times, When regenerating the second image, the training image group includes a plurality of unused images that have not been used in regenerating the second image in the past, and a proportion of the plurality of unused images in the training image group is greater than a proportion of used images that have been used in regenerating the second image in the past in the training image group.
- the training image group is selected each time the second image is generated or regenerated from among a plurality of detection target images stored in a memory.
- the training image set includes the used images.
- the training image set does not include the used image.
- the first control unit determines that at least a portion of the first image is similar to the second image, the first control unit acquires the portion as the unused image of the detection target image.
- the first control unit regenerates the second image when a number of the plurality of unused images reaches a first number.
- the first control unit regenerates the second image based on the training image group having a different number of images from when the second image was generated.
- the first control unit uses, when regenerating the second image, a number of the unused images different from a number of the unused images used during the previous regeneration.
- the first control unit performs the similarity determination by comparing the second image with the first image, and uses a plurality of stable pixels in the second image as comparison targets; The stable pixels are selected based on a similarity determination between the second image and at least one target image in the training image set.
- the number of the plurality of detection target images used to select the stable pixels is less than the number of the detection target images used to generate or regenerate the second image.
- the stable pixel is It is possible to select again, The stable pixel is selected based on at least one unused image that has not been used in any previous selection or reselection of the stable pixel.
- a percentage of the unused image used in the stable pixel reselection is different from a percentage of the unused image used to regenerate the second image.
- an image processing method includes: acquiring a first image; performing a similarity determination between a second image generated based on a training image group including a plurality of detection target images different from the first image and at least a part of the first image; and regenerating the second image based on a training image set that includes a number of unused images that are greater than the used images used to generate the second image.
- the operation device controller (15)
- the image processing device according to any one of (1) to (13) above includes a control unit capable of acquiring the similarity determination and controlling an operation device based on the similarity determination.
- the embodiment of the present disclosure can also be implemented as a method or program for implementing the device, or as a storage medium on which a program is recorded (for example, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a CD-RW, a magnetic tape, a hard disk, or a memory card, etc.).
- a storage medium on which a program is recorded for example, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a CD-RW, a magnetic tape, a hard disk, or a memory card, etc.
- the implementation form of the program is not limited to application programs such as object code compiled by a compiler or program code executed by an interpreter, but may be in the form of a program module incorporated into an operating system.
- the program may or may not be configured so that all processing is performed only by the CPU on the control board.
- the program may be configured so that part or all of it is executed by another processing unit implemented on an expansion board or expansion unit added to the board as necessary.
- the training image group includes a greater number of unused images than the number of used images, but is not limited to such a configuration.
- the number of used images included in the training image group may be the same as the number of unused images, or may be greater than the number of unused images.
- embodiments of the present disclosure are not limited to the specific configurations of any of the embodiments described above.
- the embodiments of the present disclosure may extend to any novel feature or combination of features described herein, or any novel method or process step or combination of features described herein.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
Description
)。
第1画像を取得する取得部と、
前記第1画像とは異なる複数の検出対象画像を含む訓練画像群に基づいて生成された第2画像と、前記第1画像の少なくとも一部との類似判断を行う制御部と、を備え、
前記制御部は、
前記第2画像を再生成可能であるとともに、
前記第2画像の生成に使用した使用済画像よりも多くの複数の未使用画像を含む訓練画像群に基づいて前記第2画像を再生成する。
第1画像を取得することと、
前記第1画像とは異なる複数の検出対象画像を含む訓練画像群に基づいて生成された第2画像と、前記第1画像の少なくとも一部との類似判断を行うことと、
前記第2画像の生成に使用した使用済画像よりも多くの複数の未使用画像を含む訓練画像群に基づいて前記第2画像を再生成することと、を含む。
第1画像を取得する取得部と、
前記第1画像とは異なる複数の検出対象画像を含む訓練画像群に基づいて生成された第2画像と、前記第1画像の少なくとも一部との類似判断を行う第1の制御部と、を備え、
前記第1の制御部は、
前記第2画像を再生成可能であるとともに、
前記第2画像の生成に使用した使用済画像よりも多くの複数の未使用画像を含む訓練画像群に基づいて前記第2画像を再生成する
前記第1の制御部は、前記第2画像の再生成を2回以上、実行可能であるとともに、
前記第2画像を再生成する場合に、訓練画像群は、過去の前記第2画像の再生成に使用されていない複数の未使用画像を含むとともに、前記訓練画像群内の前記複数の未使用画像の割合は、前記訓練画像群内の過去の前記第2画像の再生成に使用された使用済画像の割合よりも大きい
前記訓練画像群は、前記第2画像を生成又は再生成する場合に、メモリに記憶された複数の検出対象画像の中から都度選択される。
前記訓練画像群は、前記使用済画像を含む。
前記訓練画像群は、前記使用済画像を含まない。
前記第1の制御部は、前記第1画像の少なくとも一部が前記第2画像に類似すると判断した場合、該一部を前記検出対象画像の前記未使用画像として取得する。
前記第1の制御部は、前記複数の未使用画像の数が第1の数に達する場合、前記第2画像を再生成する。
前記第1の制御部は、前記第2画像の生成時と異なる画像の数の前記訓練画像群に基づいて、前記第2画像を再生成する。
前記第1の制御部は、第2画像の再生成時に、前回の再生成時に使用した前記複数の未使用画像の数と異なる数の前記複数の未使用画像を使用する。
前記第1の制御部は、前記第2画像と前記第1画像を比較することによって前記類似判断を行うとともに、前記第2画像のうち複数の安定的な画素を比較対象として使用し、
前記複数の安定的な画素は、前記第2画像と、前記訓練画像群中の少なくとも1つの検出対象画像との類似判断に基づいて選択される。
前記安定的な画素を選択するために用いる前記複数の検出対象画像の数は、前記第2画像の生成又は再生成に用いた前記検出対象画像の数より少ない。
前記安定的な画素は、
再選択可能であるとともに、
過去の前記安定的な画素の選択又は再選択時に使用していない少なくとも1つの未使用画像に基づいて選択される。
前記安定的な画素の再選択に使用される未使用画像の割合は、前記第2画像の再生成に使用される未使用画像の割合と異なる。
第1画像を取得することと、
前記第1画像とは異なる複数の検出対象画像を含む訓練画像群に基づいて生成された第2画像と、前記第1画像の少なくとも一部との類似判断を行うことと、
前記第2画像の生成に使用した使用済画像よりも多くの複数の未使用画像を含む訓練画像群に基づいて前記第2画像を再生成することと、を含む。
上記(1)乃至(13)のいずれかの画像処理装置における前記類否判断を取得するとともに、前記類否判断に基づいて操作機器を制御可能な制御部を備える。
11 対象操作システム
12 カメラ
13 操作機器
14 検出対象
15 トレイ
16 通信部
17 メモリ
18 制御部
19 入力部
20 操作機器コントローラ
21 制御部
ri 代表画像
wi 全体画像
Claims (15)
- 第1画像を取得する取得部と、
前記第1画像とは異なる複数の検出対象画像を含む訓練画像群に基づいて生成された第2画像と、前記第1画像の少なくとも一部との類似判断を行う第1の制御部と、を備え、
前記第1の制御部は、
前記第2画像を再生成可能であるとともに、
前記第2画像の生成に使用した使用済画像よりも多くの複数の未使用画像を含む訓練画像群に基づいて前記第2画像を再生成する
画像処理装置。 - 請求項1に記載の画像処理装置において、
前記第1の制御部は、前記第2画像の再生成を2回以上、実行可能であるとともに、
前記第2画像を再生成する場合に、訓練画像群は、過去の前記第2画像の再生成に使用されていない複数の未使用画像を含むとともに、前記訓練画像群内の前記複数の未使用画像の割合は、前記訓練画像群内の過去の前記第2画像の再生成に使用された使用済画像の割合よりも大きい
画像処理装置。 - 請求項1又は2に記載の画像処理装置において、
前記訓練画像群は、前記第2画像を生成又は再生成する場合に、メモリに記憶された複数の検出対象画像の中から都度選択される
画像処理装置。 - 請求項1から3のいずれか1項に記載の画像処理装置において、
前記訓練画像群は、前記使用済画像を含む
画像処理装置。 - 請求項1から3のいずれか1項に記載の画像処理装置において、
前記訓練画像群は、前記使用済画像を含まない
画像処理装置。 - 請求項1から5のいずれか1項に記載の画像処理装置において、
前記第1の制御部は、前記第1画像の少なくとも一部が前記第2画像に類似すると判断した場合、該一部を前記検出対象画像の前記未使用画像として取得する
画像処理装置。 - 請求項1から6のいずれか1項に記載の画像処理装置において、
前記第1の制御部は、前記複数の未使用画像の数が第1の数に達する場合、前記第2画像を再生成する
画像処理装置。 - 請求項1から7のいずれか1項に記載の画像処理装置において、
前記第1の制御部は、前記第2画像の生成時と異なる画像の数の前記訓練画像群に基づいて、前記第2画像を再生成する
画像処理装置。 - 請求項1から8のいずれか1項に記載の画像処理装置において、
前記第1の制御部は、第2画像の再生成時に、前回の再生成時に使用した前記複数の未使用画像の数と異なる数の前記複数の未使用画像を使用する
画像処理装置。 - 請求項1から9のいずれか1項に記載の画像処理装置において、
前記第1の制御部は、前記第2画像と前記第1画像を比較することによって前記類似判断を行うとともに、前記第2画像のうち複数の安定的な画素を比較対象として使用し、
前記複数の安定的な画素は、前記第2画像と、前記訓練画像群中の少なくとも1つの検出対象画像との類似判断に基づいて選択される
画像処理装置。 - 請求項10に記載の画像処理装置において、
前記安定的な画素を選択するために用いる前記複数の検出対象画像の数は、前記第2画像の生成又は再生成に用いた前記検出対象画像の数より少ない
画像処理装置。 - 請求項10又は11に記載の画像処理装置において、
前記安定的な画素は、
再選択可能であるとともに、
過去の前記安定的な画素の選択又は再選択時に使用していない少なくとも1つの未使用画像に基づいて選択される
画像処理装置。 - 請求項10から12のいずれか1項に記載の画像処理装置において、
前記安定的な画素の再選択に使用される未使用画像の割合は、前記第2画像の再生成に使用される未使用画像の割合と異なる
画像処理装置。 - 第1画像を取得することと、
前記第1画像とは異なる複数の検出対象画像を含む訓練画像群に基づいて生成された第2画像と、前記第1画像の少なくとも一部との類似判断を行うことと、
前記第2画像の生成に使用した使用済画像よりも多くの複数の未使用画像を含む訓練画像群に基づいて前記第2画像を再生成することと、を含む
画像処理方法。 - 請求項1から13のいずれか1項記載の画像処理装置における前記類似判断を取得するとともに、前記類似判断に基づいて操作機器を制御可能な第2の制御部を備える、操作機器コントローラ。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP24823431.2A EP4730269A1 (en) | 2023-06-13 | 2024-06-12 | Image processing device, image processing method, and operation device controller |
| JP2025527979A JPWO2024257816A1 (ja) | 2023-06-13 | 2024-06-12 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2023-097071 | 2023-06-13 | ||
| JP2023097071 | 2023-06-13 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024257816A1 true WO2024257816A1 (ja) | 2024-12-19 |
Family
ID=93852261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2024/021405 Ceased WO2024257816A1 (ja) | 2023-06-13 | 2024-06-12 | 画像処理装置、画像処理方法、及び操作機器コントローラ |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP4730269A1 (ja) |
| JP (1) | JPWO2024257816A1 (ja) |
| WO (1) | WO2024257816A1 (ja) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6134343A (en) * | 1996-09-24 | 2000-10-17 | Cognex Corporation | System or method for detecting defect within a semi-opaque enclosure |
| JP2015007972A (ja) * | 2013-05-31 | 2015-01-15 | オムロン株式会社 | 画像照合方法、画像照合装置、モデルテンプレート生成方法、モデルテンプレート生成装置、およびプログラム |
| JP2018151748A (ja) | 2017-03-10 | 2018-09-27 | オムロン株式会社 | 画像処理装置、画像処理方法、テンプレート作成装置、物体認識処理装置及びプログラム |
| CN112289726A (zh) * | 2020-10-29 | 2021-01-29 | 上海精测半导体技术有限公司 | 晶圆对准模板图像生成方法 |
-
2024
- 2024-06-12 JP JP2025527979A patent/JPWO2024257816A1/ja active Pending
- 2024-06-12 WO PCT/JP2024/021405 patent/WO2024257816A1/ja not_active Ceased
- 2024-06-12 EP EP24823431.2A patent/EP4730269A1/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6134343A (en) * | 1996-09-24 | 2000-10-17 | Cognex Corporation | System or method for detecting defect within a semi-opaque enclosure |
| JP2015007972A (ja) * | 2013-05-31 | 2015-01-15 | オムロン株式会社 | 画像照合方法、画像照合装置、モデルテンプレート生成方法、モデルテンプレート生成装置、およびプログラム |
| JP2018151748A (ja) | 2017-03-10 | 2018-09-27 | オムロン株式会社 | 画像処理装置、画像処理方法、テンプレート作成装置、物体認識処理装置及びプログラム |
| CN112289726A (zh) * | 2020-10-29 | 2021-01-29 | 上海精测半导体技术有限公司 | 晶圆对准模板图像生成方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| EP4730269A1 (en) | 2026-04-22 |
| JPWO2024257816A1 (ja) | 2024-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4855556B1 (ja) | 動体検出装置、動体検出方法、動体検出プログラム、動体追跡装置、動体追跡方法及び動体追跡プログラム | |
| US9202126B2 (en) | Object detection apparatus and control method thereof, and storage medium | |
| US10679358B2 (en) | Learning image automatic sorting device, learning image automatic sorting method, and learning image automatic sorting program | |
| JP5675233B2 (ja) | 情報処理装置、その認識方法及びプログラム | |
| US10769800B2 (en) | Moving object detection apparatus, control method for moving object detection apparatus, and non-transitory computer-readable storage medium | |
| US20100272351A1 (en) | Information processing apparatus and method for detecting object in image data | |
| JP2008527525A (ja) | グラフィカルなオブジェクトを検出するための方法及び電子装置 | |
| US20180122097A1 (en) | Apparatus, method, and non-transitory computer-readable storage medium for storing program for position and orientation estimation | |
| KR20130072073A (ko) | 영상 윤곽선 추출 장치 및 방법 | |
| US20170053204A1 (en) | Program generation apparatus and program generation method | |
| JP5704863B2 (ja) | 画像処理装置、画像処理方法及び記憶媒体 | |
| US20070206885A1 (en) | Imaging System And Image Processing Program | |
| US20180089529A1 (en) | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium | |
| JP5192437B2 (ja) | 物体領域検出装置、物体領域検出方法および物体領域検出プログラム | |
| KR102429337B1 (ko) | 이미지를 안정화하는 이미지 처리 장치 및 이미지를 안정화하는 방법 | |
| WO2024257816A1 (ja) | 画像処理装置、画像処理方法、及び操作機器コントローラ | |
| US20190098330A1 (en) | Coding apparatus, coding method, and recording medium | |
| US12437561B2 (en) | Method and system for detecting a type of seat occupancy | |
| JP6098320B2 (ja) | 画像処理装置、画像処理方法、および画像処理プログラム | |
| JP7795174B2 (ja) | 画像処理装置及び画像処理方法 | |
| JP2020042350A (ja) | 画像認識方法、及び画像認識プログラム | |
| JP5470529B2 (ja) | 動き検出装置、動き検出方法及び動き検出プログラム | |
| KR20230067216A (ko) | 캡처 이미지 디스플레이 제어장치 | |
| JP7253872B2 (ja) | 情報処理装置、情報処理方法、及びプログラム | |
| CN118748757B (zh) | 动态目标检测方法、装置、计算机设备及可读存储介质 |
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: 24823431 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2025527979 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2025527979 Country of ref document: JP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024823431 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024823431 Country of ref document: EP Effective date: 20260113 |
|
| ENP | Entry into the national phase |
Ref document number: 2024823431 Country of ref document: EP Effective date: 20260113 |
|
| ENP | Entry into the national phase |
Ref document number: 2024823431 Country of ref document: EP Effective date: 20260113 |
|
| ENP | Entry into the national phase |
Ref document number: 2024823431 Country of ref document: EP Effective date: 20260113 |
|
| WWP | Wipo information: published in national office |
Ref document number: 2024823431 Country of ref document: EP |