Recognition processing device, recognition processing method, and recognition processing program

Abstract

To provide a technique for more accurately detecting an object in image recognition processing.SOLUTION: The recognition processing apparatus 10 includes an image acquisition unit 11 that acquires an image, a recognition unit 12 that recognizes an object from the image, a blur calculation unit 14 that calculates a degree of blur of the image in a range of the recognized object, and a correction unit 15 that corrects the range of the object based on the degree of blur.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a recognition processing device, a recognition processing method, and a recognition processing program. [Background technology]

[0002] There is known a technology for detecting objects such as pedestrians from an image captured around a vehicle using image recognition processing such as pattern matching. For example, Patent Document 1 discloses a technology for detecting with high accuracy the range in which an object actually exists when the ground on which the object exists is wet and the reflected image of the object reflected on the ground is visible.

[0003] The technology described in Patent Document 1 estimates the distance from the imaging device to the object by detecting upper and lower symmetrical parts at the bottom of the range of the object recognized from the image generated by the imaging device, and correcting the range of the object so that the symmetrical center position of the upper and lower symmetrical parts is the lower end of the detection range of the object. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-15696 Summary of the Invention [Problem to be solved by the invention]

[0005] In reality, the image of an object reflected by the road surface may not be symmetrical from top to bottom. In this case, the technology described in Patent Document 1 may not properly detect the symmetrical parts from top to bottom, and may not properly recognize the range of the object.

[0006] The present disclosure has been made in consideration of the above circumstances, and aims to provide a technology for recognizing objects with higher accuracy in image recognition processing. [Means for solving the problem]

[0007] A recognition processing device according to one aspect of the present disclosure includes an image acquisition unit that acquires an image, a recognition unit that recognizes an object from the image, a blur calculation unit that calculates the degree of blur of the image within the range of the recognized object, and a correction unit that corrects the range of the object based on the degree of blur.

[0008] A recognition processing method according to another aspect of the present disclosure includes the steps of acquiring an image, recognizing an object from the image, calculating the degree of blur of the image within the range of the recognized object, and modifying the range of the object based on the degree of blur.

[0009] A recognition processing program of yet another aspect of the present disclosure causes a computer to perform the steps of acquiring an image, recognizing an object from the image, calculating the degree of blur of the image within the range of the recognized object, and modifying the range of the object based on the degree of blur. [Effects of the Invention]

[0010] According to an aspect of the present disclosure, a technique for recognizing objects with higher accuracy in image recognition processing can be provided. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram illustrating a configuration of a recognition device according to a first embodiment. [Figure 2] FIG. 1 is a diagram schematically illustrating an example of an image including an object. [Figure 3] 4A to 4C are diagrams illustrating an example of dividing a recognition frame into blocks by a block dividing unit according to the first embodiment. [Figure 4] FIG. 10 is a diagram illustrating the degree of image blur for each block. [Figure 5]FIG. 10 is a diagram schematically illustrating an example of an image after the recognition frame has been corrected. [Figure 6] 4 is a flowchart showing an example of a recognition processing method according to the first embodiment. [Figure 7] FIG. 10 is a block diagram illustrating the configuration of a recognition device according to a second embodiment. [Figure 8] FIG. 1 is a diagram schematically illustrating an example of an image including an object. [Figure 9] 10A and 10B are diagrams illustrating an example of dividing a recognition frame into blocks by a blur calculation unit according to the second embodiment. [Figure 10] FIG. 10 is a diagram schematically illustrating an example of an image after the recognition frame according to the second embodiment has been corrected. [Figure 11] 10 is a flowchart showing an example of processing in a recognition processing method according to a modified example of the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Specific numerical values ​​and the like shown in the embodiments are merely examples for facilitating understanding of the invention, and do not limit the present disclosure unless otherwise specified. Elements not directly related to the present disclosure are omitted from the drawings.

[0013] First embodiment FIG. 1 is a configuration block diagram of a recognition device 1 according to a first embodiment. The recognition device 1 according to the first embodiment includes a recognition processing device 10, a camera 21, and an output device 30. Each functional block of the recognition processing device 10 can be realized, for example, by a combination of hardware and software. The hardware of the recognition processing device 10 is realized by elements and mechanical devices, such as a processor such as a central processing unit (CPU) or a graphics processing unit (GPU) of a computer, and memories such as read-only memory (ROM) or random access memory (RAM). The software of the recognition processing device 10 is realized by a computer program or the like. The recognition processing device 10 includes, as functional blocks realized by a combination of hardware and software, an image acquisition unit 11, a recognition unit 12, a block division unit 13, a blur calculation unit 14, a correction unit 15, and an output control unit 16.

[0014] The recognition processing device 10 acquires an image that may include objects such as pedestrians and vehicles present in the surrounding area, and recognizes the objects included in the image. In the first embodiment, an example is shown in which the recognition processing device 10 is installed on a multifunctional utility pole used as road infrastructure equipment, such as a Smart Pole (registered trademark). The multifunctional utility pole of the first embodiment is installed, for example, on a street, and includes an antenna and communication equipment for providing wireless communication functions, and a camera 21 for capturing images of vehicles and pedestrians passing on the road. The recognition processing device 10 of the first embodiment may be fixed to a predetermined location, like a multifunctional utility pole, or may be mounted on a moving object or flying object, such as a vehicle or drone.

[0015] The camera 21 is provided on the multifunction utility pole and generates an image capturing the surroundings of the multifunction utility pole. The camera 21 is provided, for example, above the multifunction utility pole and generates an image with an angle of view looking down on the ground on which the multifunction utility pole is installed. The camera 21 of the first embodiment is a far-infrared camera that captures infrared light to generate a thermal image. However, the camera 21 of the first embodiment is not limited to this, and may be, for example, a visible light camera that captures visible light to generate a color image or a monochrome image. The image generated by the camera 21 is, for example, a moving image at 30 frames per second or 60 frames per second, but may also be a still image.

[0016] The output device 30 is a communication device that transmits the results of object recognition by the recognition processing device 10 to another device. The output device 30 transmits the object recognition results to, for example, a server used by a business operator that manages a multifunctional utility pole. The business operator that manages the multifunctional utility pole transmits the object recognition results to a device mounted on a vehicle traveling around the multifunctional utility pole or an information terminal carried by a person near the multifunctional utility pole. The output device 30 may be a communication device that transmits the object recognition results to a device mounted on a vehicle traveling around the multifunctional utility pole or an information terminal carried by a person near the multifunctional utility pole. The device mounted on a vehicle traveling around the multifunctional utility pole or the information terminal carried by a person near the multifunctional utility pole may be, for example, a vehicle infotainment system, a car navigation device, a PDA (Personal Digital Assistant), a mobile phone, a smartphone, a tablet terminal, etc.

[0017] The image acquisition unit 11 acquires an image generated by the camera 21. The image acquisition unit 11 may be an imaging control device that controls the camera 21.

[0018] The recognition unit 12 recognizes objects in the images acquired by the image acquisition unit 11. The recognition unit 12 recognizes objects in the images using a known object recognition method, such as YOLO (YOU Only Look Once), which uses a model trained on images of various objects to be recognized. The recognition unit 12 recognizes objects such as people, automobiles, bicycles and motorcycles with people on them, for example. When an object is recognized in the image, in other words, when an object captured in the image is detected, the recognition unit 12 assigns a rectangular recognition frame surrounding the recognized object. The recognition frame in the first embodiment is an example of the range of the object.

[0019] The block dividing unit 13 divides the recognition frame of the object into a plurality of blocks. The block dividing unit 13 of this embodiment divides the recognition frame of the object into a plurality of blocks in the vertical direction of the image.

[0020] The blur calculation unit 14 calculates the degree of blur in the image within the range of the object recognized by the recognition unit 12. Blur here means that the contour is unclear, that is, the edge boundary is not clear. Blur can also be said to be a small change in pixel value relative to a change in pixel position within the image. For example, the degree of blur B can be calculated using the maximum value M and variance value V of the degree of blur using the following equation (1): B=MV...Formula (1)

[0021] The blur calculation unit 14 of this embodiment calculates the degree of blur of the image for each divided block. The degree of blur of the image can be calculated by applying an existing method. The blur calculation unit 14 of this embodiment applies a Laplacian filter to the image converted to grayscale, calculates the variance of pixel values ​​from the image after application, and calculates the degree of blur of the image based on the calculated variance.

[0022] Therefore, the smaller the variance value, the greater the degree of blur in the image, and the larger the variance value, the less the degree of blur in the image. Note that the blur calculation unit 14 may calculate the degree of blur in the image using a known method such as a gradient filter or a Fourier transform.

[0023] The correction unit 15 corrects the recognition frame based on the degree of blur of the image of each block in the recognition frame. The correction unit 15 may correct the recognition frame by changing the shape of the recognition frame so that it does not include blocks where the degree of blur of the image calculated by the blur calculation unit 14 is equal to or greater than the blur threshold, or may correct the recognition frame by applying mask processing to the range of blocks where the degree of blur of the image calculated by the blur calculation unit 14 is equal to or greater than the blur threshold. When mask processing is applied to the recognition frame, the correction unit 15 further includes a mask processing unit 15B. The mask processing unit 15B corrects the recognition frame by masking the range of blocks where the degree of blur of the image calculated by the blur calculation unit 14 is equal to or greater than the blur threshold. The method of correcting the range of the object by the correction unit 15 will be described later.

[0024] The output control unit 16 generates object information about objects recognized by the recognition unit 12 and outputs it to the output device 30. Specifically, the output control unit 16 causes the output device 30 to transmit the object information to another device. The object information output by the output control unit 16 also includes object information about objects whose recognition frames have been corrected by the correction unit 15. The object information output by the output control unit 16 may include, for example, information about the type of recognized object, and the object's position, distance, movement direction, movement speed, and the like, calculated using a known method based on the recognition frame of the recognized object. The object information may include, for example, whether or not the object was recognized by the recognition unit 12 and the number of recognized objects. When the range of an object is corrected, the output control unit 16 generates object information based on the corrected range of the object.

[0025] Here, if the ground on which the object exists is wet, a reflected image of the object reflected on the ground may appear in the image taken by the camera 21. In this case, the recognition unit 12 may erroneously recognize the reflected image of the object as part of the object, and may not be able to accurately obtain the position and distance of the recognized object.

[0026] FIG. 2 is a schematic diagram illustrating an example of an image F1 including an object O1. FIG. 2 illustrates an example of an excerpt of the periphery of an object recognized by the recognition unit 12 in an image acquired by the image acquisition unit 11. In FIG. 2, the x direction is the horizontal or left-right direction of the image frame, and the y direction is the vertical or up-down direction of the image frame. In FIG. 2, due to the reflection image R1 of the person object O1 being reflected in a puddle P1 on the road, the recognition frame DE1 in the image F1 extends downward beyond the actual range of the object O1. In other words, the recognition unit 12 erroneously recognizes the range including the reflection image R1 as the object O1 and assigns the recognition frame DE1 as the range of the object O1. As a result, the recognition frame DE1 includes a lower area than the actual recognition frame of the object O1. Regarding the distance of the object included in the object information, for example, the distance from the camera 21 to the object or the distance from the multifunctional utility pole to the object is calculated based on the coordinates in the image of the lower end of the recognition frame, which is the ground position of the object. Therefore, as shown in Figure 2, if a recognition frame is assigned to the range including the reflected image R1, object information will be generated that indicates that the object is located closer to the camera 21 or the multi-functional utility pole than the actual distance to the object.

[0027] On the other hand, the outline of the reflected image R1 of the object reflected on the wet ground is often unclear. Therefore, the reflected portion of the reflected image R1 in the image of the camera 21 does not have a clear edge boundary and appears blurred. In this embodiment, the object recognition frame DE1 is corrected by taking advantage of the fact that the reflected image R1 of the object appears blurred.

[0028] A method for correcting the range of an object according to the first embodiment will be described below.

[0029] First, the block dividing unit 13 divides the recognition frame DE1 into a plurality of blocks. Fig. 3 is a diagram illustrating the division of the recognition frame DE1 into blocks by the block dividing unit 13 of the first embodiment. In the example of Fig. 3, the block dividing unit 13 divides the recognition frame DE1 into five blocks B1 to B5 arranged vertically by dividing the recognition frame DE1 at predetermined intervals in the vertical direction on the image plane of the image frame, using the top or bottom end as a reference. The intervals at which the recognition frame DE1 is divided vertically may be set as appropriate from the perspective of the accuracy of correction of the recognition frame based on, for example, the degree of blurring of the image.

[0030] Next, blur calculation unit 14 calculates the degree of blur of the image for each of divided blocks B1 to B5. Next, modification unit 15 modifies recognition frame DE1 based on the degree of blur of the image for each of blocks B1 to B5 so as to exclude a range of recognition frame DE1 where puddle P1, which is different from the object to be recognized, exists, and generates recognition frame DE2 shown in Fig. 5, which will be described later.

[0031] FIG. 4 is a diagram illustrating the degree of image blur for each of blocks B1 to B5. In FIG. 4, the vertical axis represents the degree of image blur, and the horizontal axis represents blocks B1 to B5. In the example of FIG. 4, the maximum value M of the degree of blur is set to 100. In the example of FIG. 4, the degree of image blur for blocks B1 to B3 is less than a predetermined blur threshold (e.g., 45), and the degree of image blur for blocks B4 to B5 is equal to or greater than the predetermined blur threshold. In this case, modifying unit 15 modifies recognition frame DE1 so as to exclude blocks B4 to B5, whose degree of image blur is equal to or greater than the predetermined blur threshold, from recognition frame DE1, thereby generating recognition frame DE2 shown in FIG. 5, which will be described later. The blur threshold is a reference value for determining the degree of image blur.

[0032] 5 is a diagram schematically illustrating an example of an image F1 after the recognition frame has been corrected. The correction unit 15 of the first embodiment generates a corrected recognition frame DE2 that is corrected so as not to include blocks B4 to B5, where the degree of image blur is equal to or greater than a predetermined blur threshold. When masking blocks B4 to B5, the masking is performed so that they are covered with a mask M1. The correction unit 15 generates a corrected recognition frame DE2 so that the boundary of the recognition frame DE1 on the mask M1 side is positioned so as to contact the upper end of the mask M1. In this way, the range of the object is corrected, and the appropriate ground position of the object can be obtained.

[0033] Fig. 6 is a flowchart showing an example of a recognition processing method according to the first embodiment. The processing shown in Fig. 6 is repeatedly executed, for example, every few milliseconds or for each frame captured by the camera 21.

[0034] In step S101, the image acquisition unit 11 acquires an image captured by the camera 21.

[0035] In step S102, the recognition unit 12 performs object recognition processing on the image acquired in step S101 and determines whether or not an object has been recognized in the image. If it is determined that an object has been recognized (Yes in step S102), the recognition unit 12 generates a recognition frame indicating the range of the recognized object, and the process proceeds to step S103. If the object has not been recognized (No in step S102), the process ends.

[0036] In step S103, the block dividing unit 13 divides the recognition frame of the object into blocks. Specifically, the block dividing unit 13 divides the recognition frame, which indicates the range of the object recognized by the recognition unit 12, into blocks vertically by dividing the recognition frame at predetermined intervals based on the upper or lower end of the recognition frame. Note that the intervals at which the block dividing unit 13 divides the recognition frame vertically may be set appropriately based on the degree of blurring of the image.

[0037] In step S104, the blur calculation unit 14 calculates the degree of blur of the image for each divided block. Specifically, the blur calculation unit 14 applies a Laplacian filter to an image obtained by converting the image of each divided block into grayscale, and calculates the degree of blur of the image for each divided block based on the variance of the pixel values ​​of the image to which the Laplacian filter has been applied.

[0038] In step S105, the correction unit 15 determines whether there is a block in which the degree of blur of the image is equal to or greater than the blur threshold. If there is a block in which the degree of blur of the image is equal to or greater than the predetermined threshold (Yes in step S105), the process proceeds to step S106. If there is no block in which the degree of blur of the image is equal to or greater than the predetermined threshold (No in step S105), the process ends.

[0039] In step S106, the modifying unit 15 identifies a range of blocks in which the degree of blur of the image is equal to or greater than the blur threshold. Specifically, the modifying unit 15 searches for a block in which the degree of blur of the image is equal to or greater than a predetermined blur threshold, from the top to the bottom of the divided blocks, and identifies the range of blocks from the first block in which the degree of blur of the image is equal to or greater than the blur threshold to the bottom block as the range of blocks in which the degree of blur of the image is equal to or greater than the blur threshold.

[0040] In step S107, the modifying unit 15 modifies the recognition frame based on the degree of blur of the image. Specifically, the modifying unit 15 modifies the recognition frame so as not to include the range of blocks from the block where the degree of blur of the image is equal to or greater than the blur threshold to the block at the bottom end. After step S107, the processing ends.

[0041] In the process of step 107, the mask processing unit 15B may perform mask processing on the range of blocks from the block where the degree of blur of the image is equal to or greater than the blur threshold to the block at the bottom end, thereby correcting the recognition frame.

[0042] In the first embodiment, the recognition processing device 10 includes an image acquisition unit 11 that acquires an image, a recognition unit 12 that recognizes an object from the image, a blur calculation unit 14 that calculates the degree of blur in the image within the range of the recognized object, and a correction unit 15 that corrects the range of the object based on the degree of blur. With this configuration, by correcting the range of the object based on the degree of blur in the image, it is possible to suppress erroneous recognition due to the reflection of the object in a body of water on the ground surface. This allows for more accurate recognition of objects in the image recognition process, making it possible to generate accurate object information.

[0043] The recognition processing device 10 of the first embodiment further includes a block dividing unit 13 that divides the range of a recognized object into a plurality of blocks, a blur calculation unit 14 that calculates the degree of blur for each of the divided blocks, and a correction unit 15 that corrects the range of the object so as not to include a range corresponding to a block whose degree of blur is equal to or greater than a predetermined blur threshold. With this configuration, by dividing the range of the object into blocks and calculating the degree of blur of the image for each block, the number of times the degree of blur of the image is calculated can be reduced, thereby making it possible to reduce the processing load on the recognition processing device 10.

[0044] Second embodiment 7 is a configuration block diagram of a recognition device 1 according to the second embodiment. The recognition device 1A according to the second embodiment differs from the recognition device 1 according to the first embodiment in that a high luminance determination unit 17 is provided in the functional block of a recognition processing device 10A. The following description of the second embodiment will focus on the differences from the first embodiment, and a description of the commonalities will be omitted as appropriate.

[0045] The high brightness determination unit 17 determines whether there is a high brightness portion within the recognition frame of the image whose brightness is equal to or greater than a predetermined brightness threshold. The camera 21 of the second embodiment is a far-infrared camera that captures infrared light to generate a thermal image. In the second embodiment, the object to be recognized is a vehicle.

[0046] A method for correcting the range of an object according to the second embodiment will be described with reference to FIGS. 8 to 10. FIGS. 8 to 10 show an image F2 in which a vehicle, which is an object O2, is photographed from behind. FIG. 8 is a diagram schematically illustrating an example of an image F2 including the object O2. FIG. 8 is an example in which the periphery of an object recognized by the recognition unit 12 is extracted from an image acquired by the image acquisition unit 11. In FIG. 8, the x direction is the horizontal or left-right direction of the image frame, and the y direction is the vertical or up-down direction of the image frame. In FIG. 8, due to the reflection image R2 of the vehicle object O2 being reflected in a puddle P2 on the road, the recognition frame DE3 in the image F2 extends downward beyond the actual range of the object O2. That is, the recognition unit 12 erroneously recognizes the range including the reflection image R2 as the object O2 and assigns the recognition frame DE3 as the range of the object O2. As a result, a recognition frame that includes a lower area than the actual recognition frame of the object O2 is assigned. Therefore, as shown in Figure 8, if a recognition frame is assigned to the range including the reflected image R2, object information will be generated that indicates that the object is located closer to the camera 21 or the multi-functional utility pole than the actual distance to the object.

[0047] Fig. 9 is a diagram illustrating division of the recognition frame DE3 into blocks by the blur calculation unit 14 of the second embodiment. In the example of Fig. 9, the block division unit 13 divides the recognition frame DE3 vertically at predetermined intervals, thereby dividing the recognition frame DE3 into five blocks B6 to B10 arranged vertically.

[0048] As shown in image F2, a muffler mf is provided at the bottom of a vehicle, which is object O2. Because high heat is emitted from the muffler mf at the bottom of a vehicle in motion, the area around the muffler mf is shown with high brightness in image F2, which is a thermal image. As a result, block B8, which includes the muffler mf, includes a high-brightness portion L.

[0049] FIG. 10 is a diagram schematically illustrating an example of an image F2 after a correction of the recognition frame according to the second embodiment. Taking advantage of the fact that the lower periphery of the vehicle becomes highly luminous due to the high heat emitted from the muffler mf, the correction unit 15 of the second embodiment generates a corrected recognition frame DE4 that is corrected so as not to include blocks B9 to B10 located below block B8 that includes the high-luminance portion F. When masking blocks B9 to B10, the correction unit 15 performs masking so as to cover them with mask M2. The correction unit 15 generates a corrected recognition frame DE4 so that the boundary of the recognition frame DE3 on the mask M2 side is positioned so as to contact mask M2. This corrects the range of the object, and the appropriate ground position of the object can be acquired.

[0050] Fig. 11 is a flowchart showing an example of processing in a recognition processing method according to a modified example of Embodiment 2. Steps S201 to S203 and S205 to S208 in Fig. 11 are similar to steps S101 to S107 in Fig. 6, and therefore description thereof will be omitted.

[0051] In step S204, the high brightness determination unit 17 determines whether or not there is a high brightness portion within the recognition frame of the thermal image, the brightness of which is equal to or greater than a predetermined brightness threshold. For example, the high brightness determination unit 17 detects a high brightness portion by comparing the brightness value of each pixel within the recognition frame of the image with a predetermined brightness threshold. If there is a high brightness portion (Yes in step S204), the process proceeds to step S209. If there is no high brightness portion (No in step S204), the process proceeds to step S205, and in steps S205 to S208, the recognition frame is modified as necessary based on the degree of blurring of the image.

[0052] In step S209, modifying unit 15 identifies a range of blocks below the block including the high-luminance portion. Specifically, modifying unit 15 searches from the top to the bottom of the divided blocks for a block including a high-luminance portion whose luminance is equal to or greater than a predetermined luminance, and identifies a range of blocks below the block including the high-luminance portion.

[0053] In step S210, the correction unit 15 corrects the recognition frame based on the high-brightness portion. Specifically, the correction unit 15 corrects the recognition frame so as not to include the range of blocks below a block that includes a high-brightness portion whose brightness is equal to or greater than a predetermined brightness. After step 210, the processing ends.

[0054] In the process of step 210, the mask processing unit 15B may perform mask processing on the range of blocks below the block including the high-brightness portion, thereby correcting the recognition frame.

[0055] In the second embodiment, an example has been shown in which the recognition frame is corrected based on the high-brightness portion F near the muffler mf, but the present invention is not limited to this. For example, because high heat is also emitted from an undercover that covers the engine of the vehicle, the recognition frame may be corrected based on a high-brightness portion in the undercover that covers the engine of the vehicle.

[0056] In the second embodiment, the step of determining whether or not there is a high-brightness part within the recognition frame (step S204) is executed before the step of determining whether or not there is a block where the degree of blur of the image is equal to or greater than the blur threshold (step S206), but this is not limiting. For example, if it is determined that there is no block where the degree of blur of the image is equal to or greater than the blur threshold, it may be determined whether or not there is a high-brightness part within the recognition frame.

[0057] In the second embodiment, the image is a thermal image, the object is a vehicle, and the system further includes a high-brightness determination unit 17 that determines whether the recognized object has a high-brightness area whose brightness is equal to or greater than a predetermined brightness threshold. If the correction unit 15 determines that the object has a high-brightness area, it corrects the object's area so that it does not include the area below the high-brightness area. This configuration effectively reduces false recognition due to the reflection of the object in water on the ground surface by correcting the object's area so that it does not include the area below the high-brightness area. This enables more accurate object detection in image recognition processing. The method of the second embodiment is particularly useful when the entire image is blurred due to, for example, rain or fog, and the method of the first embodiment based on the degree of image blur is unable to accurately define a recognition frame.

[0058] Several variations of the present disclosure will be described below.

[0059] In the above embodiment, the recognition frame is divided into blocks, and the degree of blur of the image is calculated for each block, but this is not limiting. For example, the degree of blur of the image may be calculated for each pixel within the recognition frame.

[0060] The present disclosure has been described above with reference to the above-mentioned embodiments, but the present disclosure is not limited to the above-mentioned embodiments, and appropriate combinations or substitutions of the configurations shown in the embodiments are also included in the present disclosure. [Explanation of symbols]

[0061] 1...recognition device, 10...recognition processing device, 11...image acquisition unit, 12...recognition unit, 13...block division unit, 14...blur calculation unit, 15...correction unit, 16...output control unit, 17...high brightness judgment unit, 21...camera, 30...output device

Claims

1. an image acquisition unit that acquires an image; a recognition unit that recognizes an object from the image; a blur calculation unit that calculates the degree of blur of the image within the range of the recognized object; a correction unit that corrects the range of the object based on the degree of blur; A recognition processing device comprising:

2. a block dividing unit that divides the range of the recognized object into a plurality of blocks; the blur calculation unit calculates the degree of blur for each of the plurality of divided blocks; The recognition processing device according to claim 1 , wherein the modifying unit modifies the range of the object so as to remove a range corresponding to the block whose degree of blur is equal to or greater than a predetermined blur threshold.

3. the image is a thermal image; the object is a vehicle; a high-brightness determination unit that determines whether or not a high-brightness portion having a brightness equal to or greater than a predetermined brightness threshold exists within the range of the recognized object; The recognition processing device according to claim 1 , wherein, when it is determined that the high-brightness portion is present within the range of the object, the correction unit corrects the range of the object so as to remove a range below the high-brightness portion.

4. acquiring an image; Recognizing an object from the image; Calculating the degree of blur of the image in the area of ​​the recognized object; modifying the extent of the object based on the degree of blur; A recognition processing method comprising:

5. On the computer, acquiring an image; Recognizing an object from the image; Calculating the degree of blur of the image in the area of ​​the recognized object; modifying the extent of the object based on the degree of blur; A recognition processing program that executes the above.

Images