Image processing device

Abstract

An image processing device according to one embodiment of the present disclosure is provided with: a grouping processing circuit capable of performing a first grouping process on the basis of distance information included in a distance image corresponding to a stereo image including a left image and a right image, capable of performing a second grouping process on the basis of color information included in a captured image, which is one of the left image and the right image, and capable of correcting the processing result of the first grouping process on the basis of the processing result of the second grouping process; and an object recognition processing circuit capable of performing object recognition processing on the basis of the corrected processing result of the first grouping process. In the second grouping process, when the value of the color difference between two adjacent pixels is equal to or less than a prescribed value, the grouping processing circuit is capable of performing the grouping process such that the two pixels belong to the same group.

Description

Image Processing Device

[0001] The present disclosure relates to an image processing device that performs object recognition of a subject.

[0002] In vehicles, object recognition processing of a subject is often performed based on stereo images generated by a stereo camera. Specifically, an image processing device of the vehicle performs grouping processing based on a distance image obtained from the stereo images, such that two adjacent pixels belong to the same group when the difference in distance values ​​between the two pixels is equal to or less than a predetermined value. Then, the image processing device performs object recognition processing based on the result of the grouping processing.

[0003] Incidentally, some image processing devices perform grouping processing using color images. For example, Patent Document 1 discloses a technology for segmenting a color image by labeling each pixel in the color image based on its color.

[0004] Japanese Patent Application Laid-Open No. 2000-67240

[0005] An image processing device according to an embodiment of the present disclosure includes a grouping processing circuit and an object recognition processing circuit. The grouping processing circuit is capable of performing a first grouping process based on distance information included in a distance image corresponding to a stereo image including a left image and a right image, and a second grouping process based on color information included in a captured image that is one of the left image and the right image, and is capable of correcting the result of the first grouping process based on the result of the second grouping process. The object recognition processing circuit is capable of performing object recognition processing based on the corrected result of the first grouping process. In the second grouping process, if a color difference value between two adjacent pixels is equal to or less than a predetermined value, the grouping processing circuit is capable of performing grouping processing such that the two pixels belong to the same group.

[0006] The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate one embodiment and, together with the description, serve to explain the principles of the disclosure.

[0007] FIG. 1 is an explanatory diagram illustrating an example configuration of a vehicle equipped with a driving assistance device according to an embodiment of the present disclosure. FIG. 2 is a block diagram illustrating an example configuration of the driving assistance device shown in FIG. 1. FIG. 3 is an explanatory diagram illustrating an example of a left image and a right image shown in FIG. 2. FIG. 4 is an explanatory diagram illustrating a CIE Lab color space. FIG. 5 is a flowchart illustrating an example operation of the driving assistance device shown in FIG. 2. FIG. 6 is an explanatory diagram illustrating an example operation of the driving assistance device shown in FIG. 2. FIG. 7 is another explanatory diagram illustrating an example operation of the driving assistance device shown in FIG. 2.

[0008] In an image processing device that performs object recognition processing, high processing accuracy in the object recognition processing is desired, and further improvement in processing accuracy is expected.

[0009] It is desirable to provide an image processing device that can improve the processing accuracy of object recognition processing.

[0010] Some exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that the following description illustrates one specific example of the present disclosure and should not be construed as limiting the present disclosure. For example, each element, including numerical values, shapes, materials, parts, the position of each part, and the connection method of each part, is merely an example and should not be construed as limiting the present disclosure. Furthermore, in the following exemplary embodiments, components not described in independent claims based on the highest concept of the present disclosure are optional and may be provided as needed. The drawings are schematic and are not intended to be drawn to scale. Throughout this specification and the drawings, components having substantially the same function and configuration are designated by the same reference numerals, and redundant description will be omitted. Furthermore, components not directly related to one embodiment of the present disclosure are not shown in the drawings.

[0011] 1 and 2 show an example of the configuration of a driving assistance device 1 equipped with an image processing device according to an embodiment. The driving assistance device 1 is mounted on a vehicle 9 and is configured to assist a driver in driving the vehicle 9. The driving assistance device 1 includes a stereo camera 10 and a processing device 20.

[0012] The stereo camera 10 is configured to capture images of the area ahead of the vehicle 9, thereby generating a set of image data having parallax from one another. In this example, as shown in FIG. 1 , the stereo camera 10 is disposed inside the vehicle 9, near the top of the windshield of the vehicle 9. The stereo camera 10 includes a left camera 11L and a right camera 11R. The left camera 11L and the right camera 11R are disposed a predetermined distance apart in the width direction of the vehicle 9. Each of the left camera 11L and the right camera 11R includes a lens and an image sensor. The left camera 11L generates a left image PL, and the right camera 11R generates a right image PR. The left image PL and the right image PR constitute a stereo image PIC.

[0013] 3 shows an example of a left image PL and a right image PR constituting a stereo image PIC. In this example, another vehicle (a preceding vehicle 8) is traveling ahead of the vehicle 9 on a road on which the vehicle 9 is traveling. The left camera 11L captures an image of the preceding vehicle 8 to generate the left image PL, and the right camera 11R captures an image of the preceding vehicle 8 to generate the right image PR. The left camera 11L and the right camera 11R are arranged at a predetermined distance apart in the width direction of the vehicle 9, and therefore the left image PL and the right image PR have a parallax corresponding to the difference in their positions.

[0014] The stereo camera 10 performs an imaging operation at a predetermined frame rate (e.g., 60 fps) to generate a series of stereo images PIC, and supplies image data of the generated series of stereo images PIC to the processing device 20.

[0015] The processing device 20 is configured to perform processing based on the left image PL and the right image PR to control the operation of the driving assistance device 1. The processing device 20 is configured using, for example, one or more processors, one or more memories, etc., and is configured to perform processing by executing a program. The processing device 20 has a distance image generation unit 21, a grouping processing unit 22, an auxiliary grouping processing unit 23, a grouping correction unit 24, an object recognition unit 25, and a driving assistance processing unit 26.

[0016] The distance image generation unit 21 is configured to generate a distance image by performing stereo matching processing based on the left image PL and the right image PR. Specifically, the distance image generation unit 21 performs stereo matching processing based on the left image PL and the right image PR to identify corresponding points including two corresponding image points (left image points and right image points). The left image points are image points in the left image PL, and the right image points are image points in the right image PR. The distance image generation unit 21 calculates a parallax value based on the difference between the positions of the left image points and the right image points, and converts this parallax value into a distance value indicating the distance from the stereo camera 10 to the subject, thereby generating a distance image.

[0017] The grouping processing unit 22 is configured to perform grouping processing based on distance information of the distance image generated by the distance image generation unit 21. Specifically, when the difference in distance value between two adjacent pixels is equal to or less than a predetermined value, the grouping processing unit 22 performs grouping processing so that these two pixels belong to the same group. As a result, in an image area consisting of multiple pixels belonging to one group, the distance values ​​become approximately continuous. The grouping processing unit 22 performs grouping processing so that, for example, multiple pixels corresponding to one subject belong to one group. For example, when the stereo image PIC includes images of multiple subjects, the grouping processing unit 22 performs this grouping processing for each of the multiple subjects to generate multiple groups corresponding to the multiple subjects.

[0018] The auxiliary grouping processor 23 is configured to perform grouping processing based on color information of a captured image, which is one of the left image PL and the right image PR. When the color difference D between two adjacent pixels is equal to or less than a predetermined value, the auxiliary grouping processor 23 performs grouping processing so that these two pixels belong to the same group. Specifically, the auxiliary grouping processor 23 calculates the color difference D using, for example, the CIE Lab color space, and performs grouping processing based on this color difference D. The CIE Lab color space is also called the L*a*b* color space.

[0019] Figure 4 shows the concept of the CIE Lab color space. The CIE Lab color space is a three-dimensional color space. L* indicates lightness, and a* and b* indicate chromaticity. Here, chromaticity includes hue and saturation. The +a* direction indicates the red direction, and the -a* direction indicates the green direction. The +b* direction indicates the yellow direction, and the -b* direction indicates the blue direction.

[0020] The auxiliary grouping processor 23 first converts the color space of the captured image, which is one of the left image PL and the right image PR, from the RGB color space to the CIE Lab color space. Specifically, the auxiliary grouping processor 23 converts the color space of the captured image, for example, from the RGB color space to the HSL color space and then from the HSL color space to the CIE Lab color space. That is, in this example, the auxiliary grouping processor 23 converts the color space of the captured image in two stages. However, this is not a limitation, and the auxiliary grouping processor 23 may convert the color space using any method. The color difference D between two adjacent pixels is the distance in the CIE Lab color space between a coordinate P1 indicated by color information of a first pixel, which is one of the two pixels, and a coordinate P2 indicated by color information of a second pixel, which is the other of the two pixels, as shown in FIG. 4 . Specifically, the color difference D is expressed by the following equation using the difference Δa* in the a* direction, the difference Δb* in the b* direction, and the difference ΔL* in the L* direction between the coordinates P1 and P2. The auxiliary grouping processing unit 23 performs grouping processing so that two adjacent pixels belong to the same group when the value of the color difference D between these two pixels is equal to or less than a predetermined value. As a result, in an image area consisting of multiple pixels belonging to one group, the values ​​of the color difference D become approximately continuous. The auxiliary grouping processing unit 23 performs grouping processing so that, for example, multiple pixels corresponding to one subject belong to one group. For example, when the captured image includes images of multiple subjects, the auxiliary grouping processing unit 23 performs this grouping processing for each of the multiple subjects, thereby generating multiple groups corresponding to the multiple subjects respectively.

[0021] The grouping correction unit 24 is configured to correct the processing result of the grouping processing unit 22 using the processing result of the auxiliary grouping processing unit 23, thereby generating grouping information indicating to which group each of multiple pixels in the captured image belongs. As described above, the grouping processing unit 22 performs grouping processing based on distance information of the distance image. Therefore, as will be described later, for example, when two objects are close to each other, the grouping processing unit 22 may determine that these two objects belong to the same group. In this case, if the two objects have different colors, the auxiliary grouping processing unit 23 may perform grouping processing such that these two objects belong to different groups. The grouping correction unit 24 corrects the processing result of the grouping processing unit 22 by using the processing result of the auxiliary grouping processing unit 23, which performs grouping processing based on color information of the captured image, as auxiliary information. This improves the accuracy of the grouping processing in the driving assistance device 1.

[0022] The object recognition unit 25 is configured to perform object recognition processing for recognizing a subject based on the left image PL, the right image PR, the distance image, and the grouping information generated by the auxiliary grouping processing unit 23 .

[0023] The driving assistance processing unit 26 is configured to provide driving assistance to the vehicle 9 based on the processing result of the object recognition processing. The driving assistance processing unit 26 controls the operation of the vehicle 9, for example, so as to notify the driver of the processing result of the object recognition processing by the object recognition unit 25. Furthermore, the driving assistance processing unit 26 is configured to perform steering control and braking control of the vehicle 9, for example, based on the processing result of the object recognition processing by the object recognition unit 25.

[0024] Here, the driving assistance device 1 corresponds to a specific example of an "image processing device" in an embodiment of the present disclosure. The grouping processing unit 22, the auxiliary grouping processing unit 23, and the grouping correction unit 24 correspond to a specific example of a "grouping processing circuit" in an embodiment of the present disclosure. The grouping processing in the grouping processing unit 22 corresponds to a specific example of a "first grouping processing" in an embodiment of the present disclosure. The grouping processing in the auxiliary grouping processing unit 23 corresponds to a specific example of a "second grouping processing" in an embodiment of the present disclosure. The stereo image PIC corresponds to a specific example of a "stereo image" in an embodiment of the present disclosure. The left image PL corresponds to a specific example of a "left image" in an embodiment of the present disclosure. The right image PR corresponds to a specific example of a "right image" in an embodiment of the present disclosure. The color difference D corresponds to a specific example of a "color difference D" in an embodiment of the present disclosure. The object recognition unit 25 corresponds to a specific example of an "object recognition processing circuit" in an embodiment of the present disclosure.

[0025] [Operation and Function] Next, the operation and function of the driving assistance device 1 of this embodiment will be described.

[0026] (Overall Operation Overview) First, the operation of the driving assistance device 1 will be described with reference to Fig. 2. The stereo camera 10 captures images of the area ahead of the vehicle 9 to generate a stereo image PIC including a left image PL and a right image PR. The processing device 20 performs object detection processing of a subject based on the stereo image PIC, and provides driving assistance for the vehicle 9 based on the processing result of the object detection processing.

[0027] 5 shows an example of the operation of the driving assistance device 1. The stereo camera 10 performs an imaging operation at a predetermined frame rate to generate a series of stereo images PIC. The processing device 20 performs the following processing each time a stereo image PIC is generated.

[0028] First, the distance image generating unit 21 generates a distance image by performing stereo matching processing based on the left image PL and the right image PR included in the stereo image PIC (step S1).

[0029] Next, the grouping processing unit 22 performs grouping processing (step S2) based on the distance information of the distance image generated by the distance image generation unit 21. Specifically, when the difference in distance value between two adjacent pixels is equal to or less than a predetermined value, the grouping processing unit 22 performs grouping processing so that these two pixels belong to the same group.

[0030] Next, the auxiliary grouping processor 23 performs grouping processing based on the color information of the right image PR (step S3). When the color difference D between two adjacent pixels is equal to or less than a predetermined value, the auxiliary grouping processor 23 performs grouping processing so that these two pixels belong to the same group.

[0031] Next, the grouping correction unit 24 corrects the processing result of the grouping processing unit 22 obtained in step S2 using the processing result of the auxiliary grouping processing unit 23 obtained in step S3, thereby generating grouping information indicating which group each of the multiple pixels in the captured image belongs to (step S4).

[0032] Next, the object recognition unit 25 performs an object recognition process to recognize the subject based on the left image PL, the right image PR, the distance image, and the grouping information generated by the auxiliary grouping processing unit 23 (step S5).

[0033] Next, the driving assistance processing unit 26 performs driving assistance for the vehicle 9 based on the processing result of the object recognition processing (step S6). Specifically, the driving assistance processing unit 26 controls the operation of the vehicle 9, for example, so as to notify the driver of the processing result of the object recognition processing by the object recognition unit 25. Furthermore, the driving assistance processing unit 26 performs steering control and braking control for the vehicle 9, for example, based on the processing result of the object recognition processing by the object recognition unit 25.

[0034] This completes the process.

[0035] Next, the operations of the grouping processing unit 22, the auxiliary grouping processing unit 23, and the grouping correction unit 24 will be described in detail using a specific example.

[0036] 6 and 7 show an example of the right image PR. A leading vehicle 8 is traveling ahead of vehicle 9. In addition, multiple vehicles are parked on the left side of the road on which vehicle 9 is traveling. A person 7 is walking immediately behind one of these vehicles, vehicle 6. In these Figures 6 and 7, the person 7 is illustrated using shading.

[0037] As shown in step S2, the grouping processing unit 22 performs grouping processing based on the distance information of the distance image generated by the distance image generation unit 21. In this example, the vehicle 6 and the person 7 are close to each other. Therefore, the distance value from the stereo camera 10 of the vehicle 9 to the vehicle 6 and the distance value from the stereo camera 10 to the person 7 are almost the same. Therefore, in this case, the difference between the distance values ​​is small, so the grouping processing unit 22 can set one group for the image area including the vehicle 6 and the person 7.

[0038] Next, as shown in step S3, the auxiliary grouping processor 23 performs grouping processing based on the color information of the right image PR. In this example, the color of the vehicle 9 and the color of the person are different from each other. Therefore, the auxiliary grouping processor 23 can set two groups corresponding to the vehicle 6 and the person 7 in the image area including the vehicle 6 and the person 7.

[0039] Next, as shown in step S4, the grouping correction unit 24 generates grouping information by correcting the processing result of the grouping processing unit 22 using the processing result of the auxiliary grouping processing unit 23. In this example, in step S2, the grouping processing unit 22 sets one group in the image region including the vehicle 6 and the person 7 based on distance information, and in step S3, the auxiliary grouping processing unit 23 sets two groups in this image region based on color information. In this way, two groups are set in the image region including the vehicle 6 and the person 7 based on color information, so it is expected that two objects will be included. Therefore, the grouping correction unit 24 corrects the processing result of the grouping processing unit 22 using the processing result of the auxiliary grouping processing unit 23, thereby setting two groups in this image region. In this way, the grouping correction unit 24 generates grouping information.

[0040] Next, as shown in step S5, the object recognition unit 25 performs object recognition processing to recognize the subject based on the left image PL, the right image PR, the distance image, and the grouping information generated by the auxiliary grouping processing unit 23. As shown in Fig. 7 , the object recognition unit 25 recognizes two objects including the vehicle 6 and the person 7, and sets an image region R1 for the vehicle 6 and an image region R2 for the person 7.

[0041] Then, as shown in step S6, the driving assistance processing unit 26 performs driving assistance for the vehicle 9 based on the processing result of the object recognition processing.

[0042] In this way, the driving assistance device 1 is capable of performing a first grouping process based on distance information included in a distance image corresponding to a stereo image PIC including a left image PL and a right image PR, and a second grouping process based on color information included in a captured image that is one of the left image PL and the right image PR (in this example, the right image PR). The driving assistance device 1 is also equipped with a grouping processing circuit (grouping processing unit 22, auxiliary grouping processing unit 23, and grouping correction unit 24) that can correct the results of the first grouping process based on the results of the second grouping process, and an object recognition processing circuit (object recognition unit 25) that can perform object recognition processing based on the corrected results of the first grouping process. In the second grouping process, the grouping processing circuit is capable of performing grouping processing so that two adjacent pixels belong to the same group when the color difference between the two adjacent pixels is equal to or less than a predetermined value. In this way, the driving assistance device 1 can perform grouping processing based on not only distance information but also color information, so that even when two objects are close to each other, as shown in Figure 6, two groups corresponding to the two objects can be set, thereby improving the accuracy of the grouping processing. As a result, the driving assistance device 1 can improve the accuracy of the object recognition processing.

[0043] Furthermore, the driving assistance device 1 performs processing based on a distance image corresponding to the stereo image PIC and a captured image (in this example, the right image PR) that is one of the left image PL and the right image PR included in the stereo image PIC. Since both the distance image and the captured image are based on the stereo image PIC, they share the same coordinate system. Therefore, the driving assistance device 1 can simplify the process of correcting the processing result of the grouping processing unit 22 using the processing result of the auxiliary grouping processing unit 23.

[0044] In the driving assistance device 1, the grouping processing circuit (the grouping processing unit 22, the auxiliary grouping processing unit 23, and the grouping correction unit 24) can convert the color space of a captured image from a first color space (e.g., an RGB color space) to a second color space (a CIE Lab color space) and can calculate color differences based on the captured image in the second color space (a CIE Lab color space). Therefore, the driving assistance device 1 can convert the RGB color space into a color space that makes it easier to calculate color differences and calculate color differences using the captured image in this color space, thereby enabling color differences to be calculated in a simple manner. As a result, the driving assistance device 1 can effectively improve the processing accuracy of object recognition processing without performing complex calculations.

[0045] In the driving assistance device 1, the second color space is the CIE Lab color space. In the driving assistance device 1, the color difference can be calculated using the CIE Lab color space, and therefore the color difference can be calculated using a simple method. As a result, the driving assistance device 1 can effectively improve the processing accuracy of the object recognition process without performing complex calculations.

[0046] In the driving assistance device 1, the two pixels include a first pixel and a second pixel, and the color difference is the distance between a first coordinate indicated by color information of the first pixel in the second color space and a second coordinate indicated by color information of the second pixel in the second color space. This allows the driving assistance device 1 to calculate the color difference using a simple method. As a result, the driving assistance device 1 can effectively improve the processing accuracy of the object recognition process without performing complex calculations.

[0047] [Effects] As described above, this embodiment is capable of performing a first grouping process based on distance information contained in a distance image corresponding to a stereo image including a left image and a right image, and a second grouping process based on color information contained in a captured image that is one of the left image PL and the right image PR. The present invention is also provided with a grouping processing circuit that can correct the results of the first grouping process based on the results of the second grouping process, and an object recognition processing circuit that can perform object recognition processing based on the corrected results of the first grouping process. In the second grouping process, the grouping processing circuit is capable of performing grouping processing so that two adjacent pixels belong to the same group if the color difference between the two adjacent pixels is equal to or less than a predetermined value. This improves the accuracy of the object recognition process.

[0048] In this embodiment, the grouping processing circuit can convert the color space of the captured image from the first color space to the second color space, and can calculate the color difference based on the captured image in the second color space. This allows the color difference to be calculated using a simple method, thereby effectively improving the processing accuracy of the object recognition process.

[0049] In this embodiment, the second color space is the CIE Lab color space, so that color differences can be calculated using a simple method, thereby effectively improving the processing accuracy of object recognition processing.

[0050] In this embodiment, the two pixels include a first pixel and a second pixel, and the color difference is the distance between a first coordinate indicated by color information of the first pixel in the second color space and a second coordinate indicated by color information of the second pixel in the second color space. This allows the color difference to be calculated using a simple method, thereby effectively improving the processing accuracy of the object recognition process.

[0051] [Modification] In the above embodiment, the auxiliary grouping processing unit 23 calculates color differences using the CIE Lab color space, but this is not limited to this. Instead, color differences may be calculated using, for example, the HSL color space or the Lch color space. Even in this case, the auxiliary grouping processing unit 23 can calculate color differences using a relatively simple method.

[0052] Although an example of an embodiment of the present disclosure has been described above with reference to the accompanying drawings, the present disclosure is by no means limited to the above embodiment. Those skilled in the art will understand that various modifications and variations can be made without departing from the scope defined by the appended claims. The present disclosure is intended to encompass such modifications and variations to the extent that they fall within the scope of the appended claims and their equivalents.

[0053] For example, in the above embodiment, as shown in Figure 5, the auxiliary grouping processing unit 23 performed grouping processing based on the color information of the right image PR, but this is not limited to this, and instead, for example, the grouping processing may be performed based on the color information of the left image PL.

[0054] The effects described in this specification are merely examples, and the effects of the present disclosure are not limited to the effects described in this specification. Therefore, other effects may be obtained with respect to the present disclosure.

[0055] Furthermore, the present disclosure may take the following aspects.

[0056] (1) An image processing device comprising: a grouping processing circuit capable of performing a first grouping process based on distance information included in a distance image corresponding to stereo images including left and right images, a second grouping process based on color information included in a captured image that is one of the left and right images, and correcting a result of the first grouping process based on a result of the second grouping process; and an object recognition processing circuit capable of performing an object recognition process based on the corrected result of the first grouping process, wherein in the second grouping process, if a color difference value between two adjacent pixels is equal to or less than a predetermined value, the grouping processing circuit is capable of performing grouping process such that the two pixels belong to the same group. (2) The image processing device described in (1), wherein the grouping processing circuit is capable of converting a color space of the captured image from a first color space to a second color space and is capable of calculating the color difference based on the captured image in the second color space. (3) The image processing device described in (2), wherein the second color space is a CIE Lab color space. (4) The image processing device according to (2) or (3), wherein the two pixels include a first pixel and a second pixel, and the color difference is a distance between a first coordinate indicated by color information of the first pixel in the second color space and a second coordinate indicated by color information of the second pixel in the second color space.

[0057] The processing device 20 shown in FIG. 2 can be implemented by circuitry including at least one semiconductor integrated circuit, such as at least one processor (e.g., a central processing unit (CPU)), at least one application-specific integrated circuit (ASIC), and / or at least one field-programmable gate array (FPGA). The at least one processor can be configured to perform all or a portion of the various functions of the processing device 20 shown in FIG. 2 by reading instructions from at least one non-transitory, tangible computer-readable medium. Such media can take various forms, including, but not limited to, various magnetic media such as hard disks, various optical media such as CDs or DVDs, and various semiconductor memories (i.e., semiconductor circuits) such as volatile or non-volatile memories. Volatile memories can include DRAM and SRAM. Non-volatile memories can include ROM and NVRAM. An ASIC is an integrated circuit (IC) specialized to perform all or a portion of the various functions of the processing device 20 shown in FIG. 2. An FPGA is an integrated circuit designed to be configurable after manufacture to perform all or a portion of the various functions of the processing device 20 shown in FIG. 2.

Claims

1. An image processing device comprising: a grouping processing circuit capable of performing a first grouping process based on distance information contained in a distance image corresponding to a stereo image including a left image and a right image, and capable of performing a second grouping process based on color information contained in a captured image that is one of the left image and the right image, and capable of correcting the result of the first grouping process based on the result of the second grouping process; and an object recognition processing circuit capable of performing an object recognition process based on the corrected result of the first grouping process, wherein in the second grouping process, if the color difference value between two adjacent pixels is equal to or less than a predetermined value, the grouping processing circuit is capable of performing grouping processing so that the two pixels belong to the same group.

2. The image processing device according to claim 1, wherein the grouping processing circuit is capable of converting the color space of the captured image from a first color space to a second color space, and is capable of calculating the color difference based on the captured image in the second color space.

3. The image processing device according to claim 2, wherein the second color space is a CIE Lab color space.

4. The image processing device according to claim 2, wherein the two pixels include a first pixel and a second pixel, and the color difference is the distance between a first coordinate indicated by color information of the first pixel in the second color space and a second coordinate indicated by color information of the second pixel in the second color space.

Images