JP5172482B2 - Vehicle periphery monitoring device - Google Patents

Description

  The present invention relates to a vehicle periphery monitoring device that monitors the periphery of a vehicle using a captured image obtained by an imaging unit mounted on the vehicle.

  Conventionally, the applicant of this type of vehicle periphery monitoring apparatus is a vehicle periphery monitoring apparatus that monitors the periphery of a vehicle using a captured image obtained by an imaging unit mounted on the vehicle, and the object is obtained from the captured image. An object extraction means for extracting the image area, a first object area in which a ratio of widths in different directions falls within a predetermined range in the image area of the object extracted by the object extraction means, and the first Object type determining means for determining the type of the object depending on whether a plurality of second object areas having an area smaller than that of the first object area are included below the object area The vehicle periphery monitoring apparatus characterized by providing is proposed (refer patent document 1). According to this prior art, it is possible to determine whether or not the type of the object is an animal having a trunk having a shape in which the ratio of the widths in different directions falls within a predetermined range.

  In addition, this type of vehicle periphery monitoring device includes a left-side photographing unit installed on the left side of the host vehicle and a right-side photographing unit installed on the right side, and images captured by the respective photographing units are stored in the vehicle. When the moving object approaching from the right side of the host vehicle is photographed by the right-side photographing means and then the approaching moving object disappears from the screen, this is indicated after the disappearance. A vehicle periphery monitoring device is known (see Patent Document 2). According to this prior art, when a vehicle displayed in the right image is detected and the vehicle disappears from the right image, it is determined that there is a possibility that occlusion occurs in the left image, and the buzzer is This can be notified to an occupant of the host vehicle by an indicator or a monitor display. Therefore, the occupant can quickly know the occurrence of occlusion.

However, if an occlusion occurs while an animal is being tracked by the imaging means mounted on the vehicle, the vehicle periphery monitoring device will be unclear whether the animal is the same before the occlusion occurrence and after the occlusion elimination. Therefore, there is a problem that it is not possible to effectively use the position information of the animals tracked before the occurrence of occlusion.
JP 2007-310705 A JP 2004-159268 A

  In view of the above problems, the present invention provides a vehicle periphery capable of highly accurately complementing the position of the animal during the occurrence of occlusion when the occlusion occurs while the animal is being tracked by the imaging means mounted on the vehicle. An object is to provide a monitoring device.

  In order to solve the above problems, a vehicle periphery monitoring device according to a first aspect of the present invention is a vehicle periphery monitoring device that monitors the periphery of a vehicle using a captured image obtained by an imaging unit mounted on the vehicle, wherein the captured image Object extraction means for extracting the image area of the object from the object, and whether the object of the image area extracted by the object extraction means is a designated animal having a head on either side of the torso Animal determination means for determining whether or not, occlusion determination means for determining whether or not occlusion in which the object disappears from the captured image has occurred during tracking of the object in the captured image, and the occlusion determination And the object extracted by the object extracting means is the designated animal by the animal determining means. The position of the designated animal during the occurrence of the occlusion is complemented based on the position of the designated animal extracted from the captured image before the occurrence of the occlusion and the position of the head with respect to the trunk. And a position complementing means.

  According to the vehicle periphery monitoring device of the first invention, if the designated animal has a head on either the left or right side of the torso, the direction in which the designated animal moves is the direction from the torso to the head. In view of the prediction, when the occlusion occurs while the designated animal is being tracked by the photographing means mounted on the vehicle, the position of the designated animal during the occurrence of the occlusion can be complemented with high accuracy.

A vehicle periphery monitoring device according to a second aspect of the present invention is a vehicle periphery monitoring device that monitors the periphery of a vehicle using a captured image obtained by an imaging unit mounted on the vehicle, wherein the image area of an object is detected from the captured image. And an animal for determining whether the object in the image area extracted by the object extraction means is a designated animal having a head on either side of the torso The occlusion is generated by the determination means, the occlusion determination means for determining whether or not the occlusion in which the object disappears from the captured image has occurred during the tracking of the object in the captured image, and the occlusion determination means. The object extracted by the object extraction means before the occurrence of occlusion and after occlusion elimination is determined to be the animal. A position of the head with respect to the torso of the designated animal extracted from the captured image before the occurrence of the occlusion and the position of the designated animal when the determination means determines that the animal is the designated animal, and the occlusion And a position complementing means for complementing the position of the designated animal during the occurrence of the occlusion based on the position of the designated animal extracted from the captured image after the resolution is resolved.

  According to the vehicle periphery monitoring device of the second aspect of the present invention, if the designated animal has a head on either the left or right side of the trunk, the direction in which the designated animal moves is the direction from the trunk to the head. In view of the fact that the position of the designated animal during the occurrence of the occlusion is predicted more accurately from the predicted position of the designated animal before the occurrence of the occlusion and the position of the designated animal after the occlusion cancellation, the photographing means mounted on the vehicle When the occlusion occurs during tracking of the designated animal, the position of the designated animal during the occurrence of the occlusion can be complemented with high accuracy.

  Further, the vehicle periphery monitoring device according to a third aspect of the present invention is the vehicle periphery monitoring device according to the second aspect of the present invention, wherein the position complementing means is located in the future on the side where the head is present with respect to the trunk of the designated animal in the captured image. The prediction area where the designated animal is predicted to be present is set, and the prediction area set based on the designated animal extracted as the object by the object extraction unit from the captured image before the occlusion occurs In addition, it is determined whether or not the designated animal extracted as the object by the object extraction unit from the captured image after the occlusion is eliminated, and the object extraction unit by the object extraction unit As a requirement that the designated animal extracted as an object is present, it is a requirement before the occurrence of occlusion and after the elimination of occlusion. Based on the position of the specified animals in respectively, characterized in that it complements the position of the designated animals in the occlusion occurs.

  According to the vehicle periphery monitoring device of the third aspect of the present invention, if the animal has a head on either the left or right side of the torso, the direction in which the animal moves is predicted to be the direction from the torso to the head. In addition, if there is a designated animal extracted as an object from the captured image after occurrence of occlusion by the object extraction means in the prediction region, the position of the designated animal during the occurrence of occlusion is more accurately determined from the designated animal before the occurrence of occlusion. In view of the prediction, when an occlusion occurs while an animal is being tracked by an imaging means mounted on the vehicle, the position of the designated animal during the occurrence of the occlusion can be complemented with high accuracy.

  The vehicle periphery monitoring device according to a fourth aspect of the present invention is the vehicle periphery monitoring device according to the third aspect, wherein the designated animal extracted as the target object by the target object extraction means from the captured image before the occlusion occurs. Whether the posture of the designated animal extracted from the captured image after the occlusion is eliminated by the object extraction means as the object is the same as the head of the designated animal The position of the designated animal during the occurrence of the occlusion is complemented when it is determined that the same is present and is determined to be the same.

  According to the vehicle periphery monitoring apparatus of the fourth aspect of the present invention, if the designated animal has a head on either the left or right side of the trunk, the direction in which the designated animal moves is the direction from the trunk to the head. In view of the fact that the position of the head relative to the torso of the designated animal is the same before and after the occurrence of occlusion, the designated animal is more accurately predicted. When the occlusion occurs while the designated animal is being tracked by the photographing means, the position of the designated animal during the occurrence of the occlusion can be complemented with high accuracy.

  An embodiment of the present invention will be described below with reference to FIGS.

  First, with reference to FIG.1 and FIG.2, the system configuration | structure of the vehicle periphery monitoring apparatus of this embodiment is demonstrated. FIG. 1 is a block diagram showing the overall configuration of the periphery monitoring device, and FIG. 2 is a perspective view showing the appearance of a vehicle (own vehicle) equipped with the periphery monitoring device. In FIG. 2, illustration of some components of the periphery monitoring device is omitted.

  With reference to FIGS. 1 and 2, the periphery monitoring device of the present embodiment includes an image processing unit 1. The image processing unit 1 is connected with two infrared cameras 2R and 2L as imaging means for capturing an image in front of the host vehicle 10, and as a sensor for detecting the traveling state of the host vehicle 10, the image processing unit 1 A yaw rate sensor 3 that detects the yaw rate, a vehicle speed sensor 4 that detects the traveling speed (vehicle speed) of the host vehicle 10, and a brake sensor 5 that detects the presence or absence of a brake operation of the host vehicle 10 are connected. Further, the image processing unit 1 displays a speaker 6 for outputting auditory alert information such as voice and the like, and images captured by the infrared cameras 2R and 2L and visual alert information. A display device 7 is connected.

  The infrared cameras 2R and 2L correspond to the imaging means in the present invention.

  Although not shown in detail, the image processing unit 1 includes electronic circuits including an A / D conversion circuit, a microcomputer (having a CPU, a RAM, a ROM, and the like), an image memory, and the like. The infrared cameras 2R, 2L, Analog signals output from the yaw rate sensor 3, the vehicle speed sensor 4, and the brake sensor 5 are converted into digital data by an A / D conversion circuit and input to a microcomputer. The microcomputer detects an object such as a person (pedestrian or person riding a bicycle) based on the input data, and the speaker detects when the detected object satisfies a predetermined alerting requirement. 6 or a display device 7 is used to execute a process for alerting the driver.

  The image processing unit 1 has functions as an object extraction unit, an animal determination unit, an occlusion determination unit, and a position complementing unit in the present invention.

  As shown in FIG. 2, the infrared cameras 2 </ b> R and 2 </ b> L are attached to the front portion (the front grill portion in the figure) of the host vehicle 10 in order to image the front of the host vehicle 10. In this case, the infrared cameras 2R and 2L are respectively disposed at a position on the right side and a position on the left side of the center of the host vehicle 10 in the vehicle width direction. These positions are symmetrical with respect to the center of the vehicle 10 in the vehicle width direction. The infrared cameras 2R and 2L are fixed so that their optical axes extend in parallel in the front-rear direction of the host vehicle 10 and the heights of the optical axes from the road surface are equal to each other. . The infrared cameras 2R and 2L have sensitivity in the far-infrared region, and the higher the temperature of the object to be imaged, the higher the level of the output video signal (the luminance of the video signal increases). have.

  In the present embodiment, the display device 7 includes a head-up display 7a (hereinafter referred to as HUD 7a) that displays image information on the front window of the host vehicle 10. As the display device 7, instead of the HUD 7a, or together with the HUD 7a, a display provided integrally with a meter for displaying a traveling state such as the vehicle speed of the host vehicle 10 or a display provided in an in-vehicle navigation device is provided. It may be used.

  Next, the overall operation of the periphery monitoring device of this embodiment will be described with reference to the flowchart of FIG. 3 is the same as the process described in FIG. 3 of Japanese Patent Application Laid-Open No. 2001-6096 and FIG. 3 of Japanese Patent Application Laid-Open No. 2007-310705 by the applicant of the present invention. The detailed description in this specification will be omitted.

  First, the image processing unit 1 acquires infrared captured images by the infrared cameras 2R and 2L (FIG. 3 / STEP 1).

  Next, the image processing unit 1 binarizes the reference image (right image) (FIG. 3 / STEP 2).

  Next, the image processing unit 1 performs the processing of STEP 3 to STEP 5 on the binarized image, and extracts an object (more precisely, an image area corresponding to the object) from the binarized image. First, the pixel group constituting the high luminance area of the binarized image is converted into run length data (FIG. 3 / STEP 3). Next, a label (identifier) is attached to each line group that overlaps in the vertical direction of the reference image (FIG. 3 / STEP 4). Next, each line group is extracted as an object (FIG. 3 / STEP 5).

  Next, the image processing unit 1 obtains the position of the center of gravity of each object extracted as described above (position on the reference image), the area, and the aspect ratio of the circumscribed rectangle (FIG. 3 / STEP 6).

  Next, the image processing unit 1 traces the object extracted in STEP 5 during the time, that is, recognizes the same object for each arithmetic processing period of the image processing unit 1 (FIG. 3 / STEP 7).

  Next, the image processing unit 1 reads the outputs (vehicle speed detection value and yaw rate detection value) of the vehicle speed sensor 4 and the yaw rate sensor 5 (FIG. 3 / STEP 8).

  On the other hand, the image processing unit 1 executes the processing of STEP 10 in parallel with the processing of STEP 7 and STEP 8. First, in the reference image, an area corresponding to each object (for example, a circumscribed square area of the object) is extracted as a search image (FIG. 3 / STEP 10). Next, the region having the highest correlation with the search image is extracted as a corresponding image that is an image corresponding to the search image (an image equivalent to the search image) (FIG. 3 / STEP 11). Next, the number of pixels of the difference between the lateral position of the center of gravity of the search image in the right image and the lateral position of the center of gravity of the corresponding image in the left image is calculated as parallax, and the distance of the object from the host vehicle 10 ( The distance in the front-rear direction of the host vehicle 10 is calculated (FIG. 3 / STEP 12).

  Next, the image processing unit 1 calculates a real space position that is a position (relative position with respect to the host vehicle 10) of each object in the real space (FIG. 3 / STEP 13).

  Next, the image processing unit 1 corrects the position X in the X direction of the real space position (X, Y, Z) of the object according to the time-series data of the turning angle obtained in STEP 8 (FIG. 3 / (STEP 14).

  Next, the image processing unit 1 obtains a movement vector of the object relative to the host vehicle 10 (FIG. 3 / STEP 15).

  Next, when a relative movement vector is obtained in STEP 15, a warning determination process for determining the possibility of contact with the detected object is performed (FIG. 3 / STEP 16).

  Next, the image processing unit 1 determines that none of the objects satisfy the alert generation requirement (there is no object corresponding to the alert generation requirement) in the attention determination process of STEP 16 (FIG. 3 / In STEP16... NO), the processing from STEP1 is resumed. If it is determined in STEP 16 that any of the objects satisfies the alert generation requirement (FIG. 3 / STEP 16... YES), the process proceeds to STEP 17 and actual alerts regarding the object that satisfies the alert generation requirement. Attention output determination processing for determining whether or not should be performed is executed (FIG. 3 / STEP 17).

  Next, when the image processing unit 1 determines that attention should be given (FIG. 3 / STEP 17... YES), the image processing unit 1 outputs a warning (FIG. 3 / STEP 18).

  If it is determined in STEP 17 that alerting is not performed (when it is determined that alerting is not performed for all objects), the determination result in STEP 17 is NO. In this case, the processing from STEP 1 is performed as it is. Is resumed.

  The above is the overall operation of the periphery monitoring device of this embodiment. In addition, the structure which performs the process of STEP1-6 by the image processing unit 1 corresponds to the target object extraction means of this invention.

  Next, an occlusion process when an occlusion that is a main part of the periphery monitoring device of the present embodiment occurs will be described.

  First, occlusion will be described with reference to FIG. FIG. 4A shows an image 40 at the time t = k before the occurrence of occlusion in which the object is tracked by the infrared cameras 2R and 2L. In the image 40, an image area 42 of the object is displayed.

  FIG. 4B is an image 44 between times t = k + 1 to t = k + n−1 when the occlusion occurs while tracking the object by the infrared cameras 2R and 2L. While the object is being tracked by the infrared cameras 2R and 2L, the object being tracked temporarily from the infrared cameras 2R and 2L is temporarily hidden due to the reason that the object is hidden by the shield when viewed from the infrared cameras 2R and 2L. It is a phenomenon that disappears.

  FIG. 4C shows an image 46 at time t = k + n after the occlusion cancellation in which the object is tracked by the infrared cameras 2R and 2L. In the image 46, an image area 42 'of the object is displayed.

  Therefore, at the time t = k + 1 to t = k + n−1 during the occurrence of occlusion, the object included in the image area 42 in FIG. 4A and the object included in the image area 42 ′ in FIG. It becomes unclear whether they are the same.

  Next, the occlusion process in this embodiment will be described with reference to the flowchart of FIG. When occlusion occurs during the overall operation of the periphery monitoring apparatus in FIG. 3, the following occlusion processing is executed.

  First, an animal determination process for determining whether or not the object in the image area extracted by the object determination process in STEPs 1 to 6 is a designated animal having a head on either the left or right side of the trunk is executed. (FIG. 5 / STEP 100). As the designated animal in the present embodiment, when the trunk is viewed from the side, the head (specifically, the first height) with respect to the trunk (specifically, the horizontally long first high-luminance image region). The animal is such that the second high-brightness image region smaller than the first high-brightness image region in the vicinity of the luminance image region is located on either the left or right side. Specific examples of designated animals include quadruped animals such as deer, sheep, dogs, and horses.

  Note that the objects in the image region extracted by the object determination process in STEPs 1 to 6 include not only the designated animal but also an artificial structure and a pedestrian.

In the animal determination process, when a feature that cannot be found in an animal is detected, the object is determined as an artificial structure. The determination process for determining that the object is an artificial structure is performed when the feature that cannot be found in an animal is detected in the image area of the object, such as the conditions shown in (a) to (d) below. Judged as an artificial structure.
(A) When the image of the object includes a portion indicating a straight edge.
(B) The corner of the image of the object is a right angle.
(C) A case where a plurality of objects having the same shape are included in the image of the object.
(D) When the image of the object matches the shape of the artificial structure registered in advance.

  When it is determined that the object is not an artificial structure, in order to remove the pedestrian from the animal of the object, a determination process is performed to determine whether the object is a pedestrian. In the determination process for determining whether or not the object is a pedestrian, it is determined whether or not the object is a pedestrian based on features such as the shape and size of the image area of the object on the grayscale image and luminance dispersion.

  Next, a prediction region setting process for setting a prediction region in which the designated animal is predicted to be present on the side where the head exists with respect to the trunk of the designated animal in the infrared cameras 2R and 2L is executed (FIG. 5 / STEP 102). The prediction area is set based on the position of the designated animal extracted as the object by the object determination process from the infrared cameras 2R and 2L before the occlusion occurs.

  If the predicted region is a designated animal with a head on either the left or right side of the torso, the direction of movement of the designated animal is predicted to be the direction from the torso to the head. It is set to the side where the head is present among the left and right sides. Specifically, as shown in FIG. 6A, which is an image at time t = k before the occurrence of occlusion, the head A2 (k) is present on the right side with respect to the trunk A1 (k). Therefore, the prediction area A (k) is set on the right side of the designated animal. In FIG. 6A, an emphasis frame F (broken line frame) is displayed on the HUD 7a in order to highlight and display the designated animal having the trunk A1 (k) and the head A2 (k).

  Next, a prediction region for determining whether or not there is an object extracted as an object by the object determination processing from the infrared cameras 2R and 2L after the occlusion is eliminated in the prediction region set in FIG. Existence processing is executed (FIG. 5 / STEP 104). Specifically, as shown in FIG. 6B, which is an image at time t = k + n (n = 2) after occlusion elimination, the object (A1 (k + n) and It is determined whether A2 (k + n)) exists.

  Next, in STEP 104, when there is an object extracted as an object by the object determination process (FIG. 5 / STEP 104... YES), the object determination is performed from the infrared cameras 2R and 2L after the occlusion is eliminated in the prediction region. A prediction area determination process is performed to determine whether or not there is a designated animal extracted as an object by the process (FIG. 5 / STEP 106). Specifically, as shown in FIG. 6B, which is an image at time t = k + n (n = 2) after occlusion elimination, the designated animal (A1 (k + n) and It is determined whether A2 (k + n)) exists.

  Next, in STEP 106, when there is a designated animal extracted as an object by the object determination process (FIG. 5 / STEP 106... YES), the posture of the designated animal extracted by the prediction area determination process is the same as that before the occurrence of occlusion. Prediction region determination processing is performed to determine whether or not the posture of the designated animal extracted as the object by the object extraction processing from the infrared cameras 2R and 2L is the same (FIG. 5 / STEP 108). Specifically, as shown in FIG. 6B, which is an image at time t = k + n (n = 2) after occlusion elimination, the designated animals (A1 (k) and A2 in FIG. 6A). It is determined whether the posture of (k)) and the posture of the designated animals (A1 (k + n) and A2 (k + n)) existing in the prediction region of FIG. 6B are the same. Note that the posture of the designated animal is whether the head is on the left or right side of the trunk.

  Next, when it is determined in STEP 108 that the posture of the designated animal extracted as the object by the object extraction process is the same (FIG. 5 / STEP 108... YES), from the infrared cameras 2R and 2L before the occlusion occurs. Based on the extracted position of the designated animal and the position of the designated animal determined by the prediction region determination process, a position complementing process for complementing the position of the designated animal in which occlusion is occurring is executed (FIG. 5 / STEP 110). Specifically, as shown in FIG. 6 (c), which is an image at time t = k + 1 during occurrence of occlusion, designated animals (A1 (k) and A2 (k)) before the occurrence of occlusion, and occlusion The positions of the designated animals (A1 (k + 1) and A2 (k + 1)) during the occurrence of occlusion are complemented with the designated animals (A1 (k + n) and A2 (k + n)) after the cancellation. In addition, the position complement processing for complementing the position of the designated animal during the occurrence of occlusion is, for example, by dividing the distance between the position of the designated animal before the occurrence of occlusion and the position of the designated animal after the occlusion is resolved into If the position of the designated animal before occurrence of occlusion is X (k) and the position of the designated animal after occlusion elimination is X (k + 2), the position complemented by the position completion processing is X ( k) + ((X (k + 2) −X (k)) ÷ 2). Since the designated animal can be tracked from time k to k + n, in FIG. 6C, emphasis is placed on the presence of the designated animal supplemented with the positions having the trunk A1 (k + 1) and the head A2 (k + 1). A frame F (broken line frame) is displayed on the HUD 7a. Similarly, as shown in FIG. 6 (b), the positions of the designated animals (A1 (k + 2) and A2 (k + 2)) after occlusion elimination are complemented, and the torso A1 (k + 2) and head A2 (k + 2) are An emphasis frame F (dashed line frame) that emphasizes the presence of the designated animal is displayed on the HUD 7a.

  Note that the configuration in which the processing of STEP 110 is executed by the image processing unit 1 corresponds to the position complementing means of the present invention.

  In addition, regardless of whether or not the posture of the designated animal is the same before and after occlusion occurrence in the prediction region (FIG. 5 / STEP 108 is omitted), occlusion is occurring due to the presence of the designated animal in the prediction region. It is also possible to complement the position of the designated animal.

  Further, regardless of the presence of the designated animal in the prediction area (FIG. 5 / STEP 106 is omitted), the position of the head relative to the trunk of the designated animal and the animal extracted from the infrared cameras 2R and 2L before the occlusion occurs , And the position of the designated animal extracted from the infrared cameras 2R and 2L after the occlusion is eliminated, the position of the designated animal during the occurrence of occlusion can be complemented.

  In addition, regardless of the presence of the designated animal before the occurrence of occlusion and after the elimination of occlusion (FIG. 5 / STEP 104 is omitted), the position of the designated animal extracted from the captured image before the occurrence of occlusion and the position of the head relative to the torso Based on the position, the position of the designated animal during the occurrence of occlusion can be complemented. The position complemented by the position complementing process in this case is, for example, X (k) + ΔX (ΔX∝ (X (k) −X (k), where X (k) is the position of the designated animal before the occurrence of occlusion. −1)) ÷ Δt).

  As described above, according to the present embodiment, if the designated animal has a head on the left or right side of the torso, the direction in which the designated animal moves is predicted to be the direction from the torso to the head, In addition, in view of the fact that if the position of the head relative to the torso of the designated animal is the same before the occurrence of occlusion and after the occlusion is resolved, the designated animal is predicted, the infrared cameras 2R and 2L mounted on the vehicle When an occlusion occurs while tracking a designated animal, the position of the designated animal during the occurrence of the occlusion can be complemented with high accuracy.

  In the present embodiment, a predetermined alert is configured based on the processing result of the image processing unit 1, but the vehicle behavior may be controlled based on the processing result. Good.

  In the above embodiment, the two infrared cameras 2R and 2L are provided. However, one infrared camera may be mounted on the host vehicle 10. In this case, the distance to the object is detected by a radar or the like.

The figure which shows the whole structure of one Embodiment of the periphery monitoring apparatus of the vehicle of this invention. The perspective view of the vehicle provided with the periphery monitoring apparatus of FIG. 3 is a flowchart showing processing of an image processing unit provided in the periphery monitoring device of FIG. 1. It is a figure for demonstrating the occlusion in this embodiment. It is a flowchart which shows the occlusion process in this embodiment. It is a figure for demonstrating the occlusion process in this embodiment.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Image processing unit (Object extraction means, animal determination means, occlusion determination means, position complementing means), 2R, 2L ... Infrared camera (imaging means)

Claims (4)

A vehicle periphery monitoring device that monitors the periphery of a vehicle using a captured image obtained by an imaging means mounted on the vehicle,
Object extraction means for extracting an image area of the object from the captured image;
Animal determination means for determining whether the object of the image region extracted by the object extraction means is a designated animal having a head on either the left or right side of the torso;
Occlusion determination means for determining whether or not occlusion in which the object disappears from the captured image occurred during tracking of the object in the captured image;
The occlusion occurs when the occlusion determination means determines that the occlusion has occurred, and the object extracted by the object extraction means determines that the animal is the designated animal. Position complementing means for complementing the position of the designated animal during the occurrence of the occlusion based on the position of the designated animal extracted from the captured image before the position and the position of the head with respect to the torso. A vehicle periphery monitoring device. A vehicle periphery monitoring device that monitors the periphery of a vehicle using a captured image obtained by an imaging means mounted on the vehicle,
Object extraction means for extracting an image area of the object from the captured image;
Animal determination means for determining whether the object of the image region extracted by the object extraction means is a designated animal having a head on either the left or right side of the torso;
Occlusion determination means for determining whether or not occlusion in which the object disappears from the captured image occurred during tracking of the object in the captured image;
It is determined by the occlusion determination means that the occlusion has occurred, and the object extracted by the object extraction means before the occurrence of occlusion and after occlusion elimination is determined by the animal determination means to be the designated animal. If
The position of the head with respect to the torso of the designated animal and the position of the designated animal extracted from the captured image before the occlusion occurs, and the designated animal extracted from the captured image after the occlusion is resolved Position complementing means for complementing the position of the designated animal during the occurrence of the occlusion based on the position of
Vehicle periphery monitoring apparatus comprising: a. In the vehicle periphery monitoring device according to claim 2,
The position complementing means sets a prediction region in which the designated animal is predicted to exist in the future on the side where the head is present with respect to the torso of the designated animal in the captured image, and before the occlusion occurs The object extraction means from the captured image after the occlusion is eliminated in the prediction region set with reference to the designated animal extracted as the object by the object extraction means from the captured image. It is determined whether or not the designated animal extracted as is present, and it is determined that the designated animal extracted as the target object from the captured image is extracted by the target object extraction unit. The occlusion is occurring based on the position of the designated animal before occurrence and after occlusion cancellation Vehicle periphery monitoring apparatus characterized by complementing the position of the specified animals. In the vehicle periphery monitoring device according to claim 3,
The designated animal extracted as the object by the object extraction unit from the captured image before the occlusion occurs, and the object extraction unit by the object extraction unit from the captured image after the occlusion is eliminated Whether or not the extracted posture of the designated animal is the same is determined based on the side where the head exists with respect to the trunk of the designated animal, and the occlusion occurs when it is determined to be the same A vehicle periphery monitoring device supplementing the position of the designated animal in the vehicle.

Images