JP2009146153A - Moving object detection device, moving object detection method and moving object detection program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect moving objects accurately irrespective of the size of the moving objects in images (even when the moving objects are distant). <P>SOLUTION: A moving object detection device 100 has an optical-flow-based moving object detection part 130 for detecting moving objects in images by an optical flow method and an inter-frame difference moving object detection part 140 for detecting moving objects in images by an inter-frame difference method, and outputs the result of detection by the optical-flow-based moving object detection part 130 or inter-frame difference moving object detection part 140 according to whether an own vehicle is stopped. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a moving object detection apparatus, a moving object detection method, and a moving object detection program for detecting a moving object from an image taken by a camera mounted on the moving object, and in particular, to a size of the moving object on the image. Regardless, the present invention relates to a mobile object detection apparatus, a mobile object detection method, and a mobile object detection program that can accurately detect a mobile object.

  For example, a blind corner monitor (hereinafter referred to as BCM; BCM) is used as a technology for preventing a traffic accident by acquiring an image that is a blind spot of a driver with a camera provided outside the vehicle and presenting the acquired image to the driver. Products such as Blind Corner Monitor) are used.

  FIG. 8 is a diagram illustrating a BCM shooting range. As shown in FIG. 8, when the vehicle 10 travels on an intersection or a T-junction with poor visibility, an image in the left-right direction of the vehicle 10 is displayed on a monitor from a BCM (for example, a prism type BCM) installed in front of the vehicle 10. By doing so, it becomes possible to confirm the vehicle 20 or other pedestrians approaching from the driver's blind spot. FIG. 9 is a diagram illustrating an example of an image captured by the BCM. In FIG. 9, the left and right images are displayed together on one monitor.

  In recent years, it is not limited to the monitor display using the BCM. For example, a moving object (a vehicle approaching the host vehicle) is detected from the image displayed by the BCM and a warning is issued to alert the driver. Technology is being developed for practical application. Note that an optical flow method is generally used as a method for detecting a moving object from within an image.

  For example, Patent Document 1 discloses a technique for detecting a moving body using an optical flow method. When an image area is considered to be an area where a short-distance object appears (short-distance area), a long-distance object is reflected. It is divided into possible regions (far-distance regions), and mobile objects are detected using a block matching method for short-distance regions and a gradient method for long-distance regions.

JP 2007-172540 A

  Generally, the moving body on the image becomes smaller as the position is farther. Therefore, when a wide-angle image such as a BCM is converted and output so that the image of the blind spot area is contained in one image, the area on the image where the moving object is present is further reduced.

  Although it is possible to detect a moving body existing in a long-distance region by using the method (gradient method) of Patent Document 1 described above, the gradient method is complicated in calculation and slow in processing, and has a small motion on the image. Because of the characteristic of detecting the noise, a lot of noise is picked up, so that there is a problem that it is impossible to accurately detect a moving object that exists far away.

  In addition, according to the optical flow-based concept (gradient method), it is a method of tracking in which direction the feature points on the frame are moving, so it detects the moving object that first appeared in the current frame. I can't.

  The present invention has been made in order to solve the above-described problems caused by the prior art, and can accurately move the moving object regardless of the size of the moving object on the image (even if the moving object exists far away). It is an object of the present invention to provide a mobile object detection device, a mobile object detection method, and a mobile object detection program that can be detected.

  In order to solve the above-described problems and achieve the object, the moving body detection device is a moving body detection device that detects a moving body from an image photographed by a camera mounted on the moving body, and is configured to detect the moving body by optical flow. The first moving body detecting means for detecting the moving body in the image, the second moving body detecting means for detecting the moving body in the image by the inter-frame difference method, and the moving body equipped with the camera are stopped. A stop determination unit that determines whether or not the vehicle is stopped, and a detection result output unit that outputs a detection result of the second moving body detection unit when the stop determination unit determines that the vehicle is stopped. Is a requirement.

  Further, in the moving body detection device, the detection result output means is detected by the first moving body detection means when the stop determination means determines that the stop is not stopped. It is a requirement to output the result.

  Further, this moving body detection device is the above-mentioned moving body detection device, wherein the second moving body detection means moves the moving body from within a predetermined image area including a road vanishing point in an image taken by the camera. It is a requirement to detect.

  Further, in the moving body detection device according to the first aspect, the first moving body detection unit is configured to detect a moving body approaching the moving body on which the camera is mounted, and to move on which the camera is mounted. It is necessary to exclude a moving body that is away from the body from the detection target.

  Further, the moving body detection method is a moving body detection method of a moving body detection device that detects a moving body from an image captured by a camera mounted on the moving body, and the moving body detection device uses the camera. A storage step of storing the captured image in a storage device; a first moving body detection step of acquiring an image from the storage device and detecting a moving body in the image by optical flow; and the first moving body The determination step determines whether or not the moving body is not detected by the detection step and the moving body on which the camera is mounted is stopped, and the image is calculated by the inter-frame difference method based on the determination result of the determination step. A second moving body detecting step for detecting a moving body within the first moving body and a detection result obtained by the first moving body detecting step or the second moving body detecting step. It is a requirement that includes a force step.

  Further, the moving body detection program stores, in a computer, a storage procedure for storing an image captured by a camera mounted on a moving body in a storage device, an image from the storage device, and an optical flow to store the image in the image. A first moving body detection procedure for detecting a moving body, and a determination for determining whether the moving body is not detected by the first moving body detection procedure and the moving body on which the camera is mounted is stopped. A second moving object detection procedure for detecting a moving object in the image by an inter-frame difference method based on a determination result of the determination procedure, and the first moving object detection procedure or the second moving object. And an output procedure for outputting a detection result by the detection procedure.

  The disclosed mobile body detection apparatus is an optimal mobile body detection system corresponding to the running state of the vehicle (optical flow system when the vehicle is not stopped, and inter-frame difference system when the vehicle is stopped). ) Is used to detect the moving object, so that the moving object can be accurately detected regardless of the size of the moving object on the image (even when the moving object exists far away).

  In addition, since the disclosed moving body detection device detects a moving body from within a predetermined image area including a road vanishing point in an image taken by a camera, the influence of noise can be reduced.

  In addition, the disclosed mobile object detection device targets a mobile object approaching a mobile object equipped with a camera, and excludes a mobile object that moves away from the mobile object equipped with a camera from the detection object. Can notify the hand.

  In addition, the disclosed moving body detection method includes an optimal moving body detection method corresponding to the traveling state of the vehicle (an optical flow method when the vehicle is not stopped, and an interframe frame when the vehicle is stopped). Since the moving object is detected by using the difference method, the moving object can be accurately detected regardless of the size of the moving object on the image (even when the moving object exists far away). .

  Exemplary embodiments of a mobile object detection device, a mobile object detection method, and a mobile object detection program according to the present invention will be explained below in detail with reference to the accompanying drawings.

  First, the outline and features of the moving object detection apparatus according to the first embodiment will be described. The moving body detection apparatus according to the first embodiment uses a detection method when detecting a moving body from an image captured by a camera (for example, a blind corner monitor; BCM) according to the traveling state of the vehicle on which the camera is mounted. Select and output the detection result by the selected detection method.

  Specifically, the moving body detection device detects the moving body from the image by the optical flow method when the vehicle is not stopped, and by the inter-frame difference method when the vehicle is stopped. Detect moving objects from the screen.

  FIG. 1 is a diagram for explaining the features of the optical flow method and the inter-frame difference method. As shown in the figure, the optical flow method has high detection accuracy of the moving object when the host vehicle is running, but it has newly detected the moving object near the vanishing point (near the position far away from the camera) and the current frame. There is a feature that the accuracy of detection of the generated moving body is low. On the other hand, the inter-frame difference method has a feature that detection of a moving object near the vanishing point and detection of a moving object newly generated in the current frame are high, but detection accuracy of the moving object when the vehicle is traveling is low. is there.

  As described above, the moving body detection apparatus according to the first embodiment has an optimal moving body detection method corresponding to the traveling state of the vehicle (when the vehicle is not stopped, the optical flow method, the vehicle is stopped). In this case, since the detection of the moving object is performed using the inter-frame difference method), the moving object is accurately detected regardless of the size of the moving object on the image (even when the moving object exists far away). Can be detected.

  Next, the configuration of the moving object detection apparatus according to the first embodiment will be described. FIG. 2 is a diagram illustrating the configuration of the moving object detection device 100 according to the first embodiment. As shown in the figure, the moving body detection apparatus 100 includes an image input unit 110, a vehicle stop determination unit 120, an optical flow moving body detection unit 130, an inter-frame difference moving body detection unit 140, and a moving body notification. Unit 150. Although not shown in the figure, it is assumed that the moving body detection apparatus 100 shown in FIG. 2 is connected to a camera such as a blind corner monitor and is installed in a vehicle.

  The image input unit 110 is a unit that outputs information of an input image to the optical flow moving body detection unit 130 and the inter-frame difference moving body detection unit 140 when an image input from the camera (BCM) is received.

  The vehicle stop determination unit 120 is connected to a vehicle speed detection device (not shown) and a brake sensor (not shown) in the vehicle, and stops the vehicle based on vehicle speed information and brake information input from the vehicle speed detection device. It is a means for determining whether or not. The vehicle stop determination unit 120 outputs the determination result to the inter-frame difference moving body detection unit 140.

  Specifically, the vehicle stop determination unit 120 determines that the vehicle is stopped when the vehicle speed is less than the threshold and the brake is depressed. On the other hand, the vehicle stop determination unit 120 determines that the vehicle has not stopped when the speed of the vehicle is equal to or higher than the threshold or the brake is not depressed.

  The optical flow moving body detection unit 130 is means for detecting a moving body from an image input from the image input unit 110 by an optical flow method using a block matching method. The optical flow moving body detection unit 130 outputs the detection result to the inter-frame difference moving body detection unit 140 and the moving body notification unit 150.

  Here, when the optical flow moving body detection unit 130 is described by defining the frame of the current image as n frames and the frame immediately before the n frame as n−1 frames, for example, optical flow moving body detection is performed. The unit 130 extracts block information (including pixel value information included in the predetermined area) from the predetermined area in the n-1 frame image, and the extracted block information and each of the n frame images included in the n frame image The moving object is detected by comparing the pixel value and specifying an n-frame image region that matches the block information (by executing matching).

  That is, if the coordinates of the block information extracted from the n-1 frame image and the coordinates of the area that matches the block information on the n frame image are different, the moving object exists in the image included in the block information. It will be. In addition, when the time interval between two frames is less than a threshold value, a moving body may not be detected correctly. In this case, the optical flow moving body detection unit 130 may control the camera (not shown) so that the time interval between the two frames is equal to or greater than the threshold value.

  The inter-frame difference mobile body detection unit 140 acquires the determination result from the vehicle stop determination unit 120, acquires the detection result from the optical flow mobile body detection unit 130, the own vehicle is in a stopped state, and the optical flow movement This is means for detecting a moving object from an image input from the image input unit 110 when the moving object is not detected by the body detecting unit 130.

  Specifically, the inter-frame difference moving body detection unit 140 calculates the difference between the luminance value of the n-frame image and the luminance value of the n-1 frame image (calculates the luminance difference at the same pixel position), and the difference is A moving object is detected by specifying an area that is equal to or greater than the threshold. The inter-frame difference moving body detection unit 140 outputs the detection result to the moving body notification unit 150.

  When the detection result is obtained from the optical flow moving body detection unit 130 and the inter-frame difference moving body detection unit 140, the moving body notification unit 150 uses a monitor or a speaker (not shown) to move the moving body to the driver. It is a means to notify. FIG. 3 is a diagram illustrating an example of an image on a monitor when a moving body is detected. As shown in the figure, the moving body is surrounded by a rectangle, and the driver can find the moving body at an early stage.

  The moving body notification unit 150 determines the urgent level of warning from the relationship between the area occupied by the detected moving body in the image and the image position, and surrounds the moving body in the monitor in a rectangle according to the urgency level. Alternatively, when the urgency level is equal to or greater than a predetermined value, a warning type may be selected according to the urgency level, such as a warning by voice, and the driver may be warned.

  Next, a processing procedure of the moving object detection apparatus 100 according to the first embodiment will be described. FIG. 4 is a flowchart of the process procedure of the moving object detection apparatus 100 according to the first embodiment. As shown in the figure, in the moving body detection apparatus 100, the optical flow moving body detection unit 130 detects a moving body based on the optical flow method (step S101), and determines whether or not the moving body is detected. Determination is made (step S102).

  And when a mobile body is detected (step S103, Yes), it transfers to step S109. On the other hand, when the moving body is not detected (No at Step S103), the vehicle stop determination unit 120 determines whether or not the vehicle is stopped (Step S104).

  Here, when the vehicle is not in a stopped state (step S105, No), the process proceeds to step S101. On the other hand, when the vehicle is in a stopped state (step S105, Yes), the inter-frame difference moving body detection unit 140 detects a moving body based on the inter-frame difference method (step S106), and the moving body Is detected (step S107).

  And when a mobile body is detected (step S108, Yes), the mobile body notification part 150 outputs a detection result (step S109), and transfers to step S101. On the other hand, when the moving body is not detected (step S108, No), the process proceeds to step S101 as it is.

  As described above, when the optical flow moving body detection unit 130 does not detect the moving body, the inter-frame difference moving body detection unit 140 executes the moving body detection process according to the traveling state of the host vehicle. A moving object can be accurately detected by compensating for the weak point of the moving object detection method.

  As described above, the moving object detection apparatus 100 according to the first embodiment includes the optical flow moving object detection unit 130 that detects the moving object in the image by the optical flow method, and the moving object in the image by the inter-frame difference method. The inter-frame difference moving body detection unit 140 is detected, and the detection result by the optical flow moving body detection unit 130 or the inter-frame difference moving body detection unit 140 is output according to the stop state. Regardless of the size of the body on the image (even when the moving body is located far away), the moving body can be accurately detected.

  Although the embodiments of the present invention have been described so far, the present invention may be implemented in various different forms other than the first embodiment described above. Therefore, another embodiment included in the present invention will be described below as a second embodiment.

(1) Regarding detection target For example, in the first embodiment, the optical flow moving body detection unit 130 detects all the moving bodies on the screen based on the block matching method, and the detection result is sent to the moving body notification unit 150. Although the case of outputting has been described, the present invention is not limited to this, and only a moving body that affects the host vehicle may be detected as a moving body. FIG. 5 is a diagram for explaining a moving body that is a detection target and a moving body that is not a detection target.

  As shown on the left side of FIG. 5, the optical flow moving body detection unit 130 excludes, from the detection target, a moving body that moves outward from the image center side, in other words, a moving body that moves away from the host vehicle. On the other hand, the optical flow moving body detection unit 130 detects a moving body that moves from the outside of the image to the image center side, that is, a moving body that approaches the host vehicle.

  As described above, the optical flow moving body detection unit 130 prevents the driver from notifying unnecessary information by excluding the moving body from the detection target according to the moving direction of the moving body. It is possible to prevent the driving from being hindered. Note that the inter-frame difference moving body detection unit 140 may also limit the detection target according to the moving direction of the moving body, similarly to the optical flow moving body detection unit 130.

(2) Regarding an image region that obtains a difference using an inter-frame difference method For example, in the first embodiment, when the inter-frame difference moving body detection unit 140 obtains a difference in luminance value between n frames and n−1 frames. However, the present invention is not limited to this. For example, the image is moved by comparing only the luminance values of a predetermined area including the vanishing point of the image included in each frame. The body may be detected.

  FIG. 6 is a diagram illustrating vanishing points in an image and regions to be compared. In the example shown in the figure, there are two vanishing points, and the inter-frame difference moving body detection unit 140 extracts the luminance value of a predetermined area including the vanishing point from each frame, A moving body can be detected by taking the difference. Thus, by limiting the region to be compared to the vicinity of the vanishing point, the influence of noise can be reduced.

  The method for calculating the vanishing point by the inter-frame difference moving body detection unit 140 may use any known method. For example, the inter-frame difference moving body detection unit 140 creates a differential image of the image. The vanishing point can be calculated by binarizing the edge image, performing a Hough transform using the binarized edge image as a feature point, calculating a straight line, and obtaining an intersection of the straight lines. it can.

(3) Regarding a camera that captures an image For example, in Embodiment 1 described above, an image is acquired using BCM. However, the present invention is not limited to this. Essentially, any device may be used as long as it is a photographing means capable of photographing an image including a vanishing point. For example, the moving body detection device acquires the image of the side mirror and detects the moving body behind the vehicle, thereby notifying the driver of the existence of a motorcycle or the like existing behind the vehicle and preventing the motorcycle from being involved. I can do it.

(4) System Configuration Of the processes described in the present embodiment, all or part of the processes described as being automatically performed can be performed manually or manually. All or part of the processing described as being performed can be automatically performed by a known method. In addition, the processing procedure, control procedure, specific name, and information including various data and parameters shown in the above-described document and drawings can be arbitrarily changed unless otherwise specified.

  Further, each component of the moving object detection apparatus 100 shown in FIG. 2 is functionally conceptual and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. Furthermore, each processing function performed by each device may be realized by a CPU and a program that is analyzed and executed by the CPU, or may be realized as hardware by wired logic.

  FIG. 7 is a diagram illustrating a hardware configuration of the computer 200 included in the moving object detection apparatus 100 according to the first embodiment. As shown in FIG. 7, the computer (moving body detection device) 200 includes an input device 201, a monitor 202, a camera (BCM) 203, a RAM (Random Access Memory) 204, a ROM (Read Only Memory) 205, and a storage medium. A medium reading device 206 that reads data, a communication device 207 that transmits and receives data to and from other devices, a vehicle speed detection device 208 that detects the speed of the vehicle, and a brake sensor that detects whether or not the driver has stepped on the brake 209, a CPU (Central Processing Unit) 210, and an HDD (Hard Disk Drive) 211 are connected by a bus 212.

  The HDD 211 stores an optical flow moving body detection program 211b, an inter-frame difference moving body detection program 211c, a vehicle stop determination program 211d, and a notification program 211e that exhibit the same functions as the functions of the moving body detection device 100 described above. Has been. The CPU 210 reads and executes the optical flow moving body detection program 211b, the inter-frame difference moving body detection program 211c, the vehicle stop determination program 211d, and the notification program 211e, so that the optical flow moving body detection process 210a, the inter-frame difference moving body. A detection process 210b, a vehicle stop determination process 210c, and a notification process 210d are activated.

  Here, the optical flow moving body detection process 210a corresponds to the optical flow moving body detection unit 130 of FIG. 2, and the inter-frame difference moving body detection process 210b corresponds to the inter-frame difference moving body detection unit 140, and stops the vehicle. The determination process 210 c corresponds to the vehicle stop determination unit 120, and the notification process 210 d corresponds to the moving body notification unit 150.

  Further, the HDD 211 stores various data 211 a corresponding to information (image information or the like) used in the moving object detection apparatus 100. The CPU 210 reads out various data 211 a stored in the HDD 211, stores it in the RAM 204, and detects a moving object from the image using the various data 204 a stored in the RAM 204.

  By the way, the optical flow moving body detection program 211b, the interframe difference moving body detection program 211c, the vehicle stop determination program 211d, and the notification program 211e shown in FIG. 7 do not necessarily need to be stored in the HDD 211 from the beginning. For example, a “portable physical medium” such as a flexible disk (FD), a CD-ROM, a DVD disk, a magneto-optical disk, or an IC card inserted into a computer, or a hard disk drive (HDD) provided inside or outside the computer. The "fixed physical medium", and the "another computer (or server)" connected to the computer via the public line, the Internet, LAN, WAN, etc. A differential moving body detection program 211c, a vehicle stop determination program 211d, and a notification program 211e are stored, and the computer uses them to store an optical flow mobile body detection program 211b, an interframe difference mobile body detection program 211c, and a vehicle stop determination program. Grams 211d, reads the notification program 211e may be executed.

  The following additional notes are disclosed with respect to the embodiments including Examples 1 and 2 above.

(Supplementary note 1) A moving body detection apparatus for detecting a moving body from an image taken by a camera mounted on the moving body,
First moving body detection means for detecting a moving body in the image by optical flow;
Second moving body detecting means for detecting a moving body in the image by an inter-frame difference method;
Stop determination means for determining whether or not the moving body equipped with the camera is stopped;
A detection result output unit that outputs a detection result by the second moving body detection unit when the stop determination unit determines that the stop is stopped;
A moving body detection apparatus comprising:

(Additional remark 2) The said detection result output means outputs the detection result by the said 1st moving body detection means, when the said stop determination means determines with not having stopped, Additional remark 1 characterized by the above-mentioned. Mobile object detection device.

(Additional remark 3) The said 2nd moving body detection means detects a mobile body from the predetermined image area | region containing a road vanishing point in the image image | photographed with the said camera. The moving body detection apparatus of description.

(Additional remark 4) The said 1st moving body detection means makes the detection object the moving body which approaches the moving body which mounts the said camera, and excludes the moving body which leaves | separates from the moving body which mounts the said camera from detection object. 4. The moving object detection device according to appendix 1, 2, or 3, which is characterized.

(Additional remark 5) It is a moving body detection method of the moving body detection apparatus which detects a moving body from the image image | photographed with the camera mounted in the moving body,
The mobile object detection device is:
A storage step of storing an image captured by the camera in a storage device;
A first moving body detection step of acquiring an image from the storage device and detecting a moving body in the image by optical flow;
A determination step of determining whether or not the moving body is not detected by the first moving body detection step and the moving body on which the camera is mounted is stopped;
A second moving object detection step of detecting a moving object in the image by an inter-frame difference method based on a determination result of the determination step;
An output step of outputting a detection result by the first moving body detection step or the second moving body detection step;
A moving object detection method comprising:

(Additional remark 6) The said 2nd moving body detection step detects a moving body from the predetermined image area | region containing a road vanishing point in the image image | photographed with the said camera. Moving object detection method.

(Supplementary note 7) The first moving body detecting step includes detecting a moving body approaching the moving body mounted with the camera and excluding the moving body moving away from the moving body mounted with the camera from the detection target. The moving body detection method according to appendix 5 or 6, characterized by the above.

(Appendix 8)
A storage procedure for storing an image taken by a camera mounted on a moving body in a storage device;
A first moving object detection procedure for acquiring an image from the storage device and detecting a moving object in the image by optical flow;
A determination procedure for determining whether or not the moving object is detected by the first moving object detection procedure and the moving object on which the camera is mounted is stopped;
A second moving object detection procedure for detecting a moving object in the image by an inter-frame difference method based on a determination result of the determination procedure;
An output procedure for outputting a detection result by the first moving object detection procedure or the second moving object detection procedure;
A moving body detection program for executing

(Additional remark 9) The said 2nd moving body detection procedure detects a mobile body from the predetermined image area | region containing a road vanishing point in the image image | photographed with the said camera, The additional remark 8 characterized by the above-mentioned. A moving object detection program.

(Supplementary Note 10) The first moving body detection procedure includes detecting a moving body approaching the moving body mounted with the camera as a detection target and excluding a moving body moving away from the moving body mounted with the camera from the detection target. Item 10. The moving object detection program according to appendix 8 or 9,

  As described above, the mobile object detection device, the mobile object detection method, and the mobile object detection program according to the present invention are useful for a mobile object detection system that detects a mobile object, and in particular, the size of the mobile object on the image. Regardless, it is suitable when it is necessary to accurately detect a moving object.

It is a figure for demonstrating the characteristic of the optical flow system and the difference method between frames. 1 is a diagram illustrating a configuration of a moving object detection device according to a first embodiment. It is a figure which shows the example of a monitor's image at the time of detecting a moving body. 3 is a flowchart illustrating a processing procedure of the moving object detection device according to the first embodiment. It is a figure for demonstrating the mobile body used as a detection target, and the mobile body used as a detection target outside. It is a figure which shows the vanishing point in an image, and the area | region used as a comparison object. It is a figure which shows the hardware constitutions of the computer which comprises the moving body detection apparatus concerning Example 1. FIG. It is a figure which shows the imaging | photography range of BCM. It is a figure which shows an example of the image image | photographed by BCM.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Mobile body detection apparatus 110 Image input part 120 Vehicle stop determination part 130 Optical flow mobile body detection part 140 Inter-frame difference mobile body detection part 150 Mobile body notification part

Claims (6)

A moving body detection device for detecting a moving body from an image taken by a camera mounted on the moving body,
First moving body detection means for detecting a moving body in the image by optical flow;
Second moving body detecting means for detecting a moving body in the image by an inter-frame difference method;
Stop determination means for determining whether or not the moving body equipped with the camera is stopped;
A detection result output unit that outputs a detection result by the second moving body detection unit when the stop determination unit determines that the stop is stopped;
A moving body detection apparatus comprising:   The mobile body according to claim 1, wherein the detection result output means outputs a detection result by the first mobile body detection means when the stop determination means determines that the stop is not stopped. Detection device.   3. The movement according to claim 1, wherein the second moving body detecting unit detects the moving body from within a predetermined image area including a road vanishing point in an image photographed by the camera. Body detection device.   The first moving body detection means sets a moving body approaching a moving body mounted with the camera as a detection target, and excludes a moving body moving away from the moving body mounted with the camera from the detection target. Item 4. The moving object detection device according to Item 1, 2 or 3. A moving body detecting method of a moving body detecting device for detecting a moving body from an image photographed by a camera mounted on the moving body,
The mobile object detection device is:
A storage step of storing an image captured by the camera in a storage device;
A first moving body detection step of acquiring an image from the storage device and detecting a moving body in the image by optical flow;
A determination step of determining whether or not the moving body is not detected by the first moving body detection step and the moving body on which the camera is mounted is stopped;
A second moving object detection step of detecting a moving object in the image by an inter-frame difference method based on a determination result of the determination step;
An output step of outputting a detection result by the first moving body detection step or the second moving body detection step;
A moving object detection method comprising: On the computer,
A storage procedure for storing an image taken by a camera mounted on a moving body in a storage device;
A first moving object detection procedure for acquiring an image from the storage device and detecting a moving object in the image by optical flow;
A determination procedure for determining whether or not the moving object is detected by the first moving object detection procedure and the moving object on which the camera is mounted is stopped;
A second moving object detection procedure for detecting a moving object in the image by an inter-frame difference method based on a determination result of the determination procedure;
An output procedure for outputting a detection result by the first moving object detection procedure or the second moving object detection procedure;
A moving body detection program for executing

Images