JP2003271968A - Device and method for detecting mobile-body - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To surely detect a mobile body while reducing a load for arithmetic processing when the mobile body is detected. <P>SOLUTION: This mobile body detector is provided with cameras 10a, 10b installed on a vehicle to image a prescribed range, a mobile body detecting means 20 for detecting other moving vehicle in a periphery of the vehicle, based on a differential processing result between the first image imaged by the cameras 10a, 10b, and the second image imaged after a prescribed lapse time counted from the imaging of the first image, and a time setting means 20 for shortening the prescribed time in accompaniment to getting close in a distance between the other moving vehicle and the own vehicle. The moving vehicle is surely detected thereby, in any time when the moving vehicle exists in a distant/near place. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a moving body detecting apparatus for detecting another moving body such as a vehicle approaching the moving body based on an image taken by a camera provided on the moving body.

[0002]

2. Description of the Related Art There is known a technique in which a camera provided in a vehicle captures an image of the surroundings of the vehicle and detects a moving body such as a vehicle approaching the vehicle based on the captured image. According to the technique disclosed in Japanese Patent Laid-Open No. 2001-167288, movement of a vehicle or the like is performed by capturing an image of the surroundings with a camera fixed on a road and extracting a difference between two images having different image capturing times. The body is being extracted. Further, when the moving body is moving far away from the camera, it is difficult for the difference to appear. Therefore, by performing the difference processing with at least two different time differences, the moving body exists in either the distant or the vicinity. Even when it does, it is configured to be able to reliably detect the moving body.

[0003]

However, according to the conventional technique, it is necessary to perform the difference processing at least twice using a plurality of images captured at different time intervals, which results in a load of the arithmetic processing. There was a problem of increase.

An object of the present invention is to provide a moving body detecting apparatus and a moving body detecting method capable of surely detecting a moving body while reducing the load of arithmetic processing.

[0005]

The present invention will be described with reference to FIGS. 1 and 2 showing an embodiment. (1) According to the invention of claim 1, the image pickup means 10a and 10b installed in the moving body 1 for picking up an image of a predetermined range, and the image pickup means 10 are provided.
a, 10b, and a second image captured after a predetermined time has elapsed from the time when the first image was captured.
Moving body detecting means 20 for detecting another moving body that is relatively displaced with respect to the moving body 1 based on the difference processing result with the image of
And the time setting means 20 that shortens the predetermined time as the distance between the other moving body and the moving body 1 becomes shorter,
To achieve the above objectives. (2) The invention of claim 2 is the moving object detecting device according to claim 1, wherein the time setting means 20 is configured to detect other moving objects in one of the first image and the second image. It is characterized in that the distance between another moving body and the moving body 1 is determined based on the position in the lateral direction. (3) The invention of claim 3 is the moving body detecting device according to claim 1 or 2, wherein the moving amount is detected based on the first image and the second image. It further comprises an amount detecting means 20, and the time setting means 20 is characterized by setting a predetermined time so that the moving amount detected by the moving amount detecting means 20 becomes constant. (4) In the invention of claim 4, the first image captured by the image capturing means 10a, 10b installed in the moving body 1 and capturing a predetermined range, and a predetermined time from the time when the first image is captured. In a moving body detection method for detecting another moving body that is relatively displaced with respect to the moving body 1, based on a difference processing result with a second image captured later, the other moving body and the moving body 1
The shorter the predetermined time is, the shorter the predetermined time is. (5) The invention of claim 5 is the method for detecting a moving object according to claim 4, wherein the distance between the other moving object and the moving object 1 is one of the first image and the second image. It is characterized in that it is determined on the basis of the lateral position of another moving body inside. (6) The invention of claim 6 is the method for detecting a moving object according to claim 4 or 5, wherein the moving amount of another moving object in the image is detected based on the first image and the second image. The predetermined time is set so that the detected movement amount of the other moving body becomes constant.

In the section of means for solving the above-mentioned problems, in order to explain the present invention in an easy-to-understand manner, it corresponds to FIG. 1 and FIG. 2 of the embodiment. It is not limited.

[0007]

The present invention has the following effects. (1) According to the inventions of claims 1 to 6, the first image and the first image
When a moving object is detected by difference processing with the second image captured after a predetermined time has elapsed from the time when the image of
The shorter the distance between the moving body equipped with the image pickup means and the other moving body, the shorter the predetermined time of the image pickup interval. Therefore, it is not necessary to execute the difference processing a plurality of times, and the calculation load of the moving body detection processing is reduced. be able to. (3) According to the inventions of claims 3 and 6, it is possible to reliably detect the other moving body regardless of the moving speed of the other moving body.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS (First Embodiment) FIG. 1 is a diagram showing a configuration of a first embodiment of a moving body detection apparatus according to the present invention. The moving body detection device according to the first embodiment is
Front side cameras 10a and 10b and image processing ECU 20
An alarm ECU 30, a vehicle speed sensor 40, an alarm indicator 50, an alarm buzzer 60, and an in-vehicle monitor 70.
With. As shown in FIG. 2, the front and side cameras 10a and 10b are installed on the left and right of the front side of the vehicle 1, respectively. The camera 10a is for capturing the left side of the vehicle 1 in the traveling direction, and the camera 10b is for capturing the right side of the vehicle 1 in the traveling direction.

The image processing ECU 20 includes a front side camera 10
Processing such as difference processing and moving body extraction processing is performed on the images captured in a and 10b. Various types of processing such as image processing performed by the image processing ECU 20 will be described later with reference to the flowcharts shown in FIGS. 6 to 9 and 11. The image after the image processing is sent to the alarm ECU 30 and
It is displayed on the in-vehicle monitor 70 according to a predetermined condition. The warning ECU 30 determines the degree of danger of the host vehicle based on the image after image processing and the vehicle speed detected by the vehicle speed sensor 40. When the warning ECU 30 determines that the vehicle is dangerous, the warning indicator 50 and the warning buzzer 60 are displayed.
To warn the driver.

FIG. 3 shows an image of the right side of the vehicle 1 taken by the front side camera 10b when the vehicle 1 equipped with the moving body detecting apparatus according to the present embodiment approaches an intersection such as a T-shaped road as shown in FIG. It is a figure when it did. 3 (a)-(c)
The difference in the apparent amount of movement on the image when a moving body such as a vehicle exists in the distance and in the vicinity of the camera 10b will be described with reference to. 3A to 3C respectively show three images captured at a constant time interval ΔT. In these images, the vehicle 100 approaching the vehicle 1 is shown.

The approaching vehicle 100 is smaller in the image as it is farther from the camera 10b (own vehicle 1) (see FIG. 3).
(A)), as it approaches the camera 10b, it becomes larger in the image (FIG. 3 (c)). Therefore,
Even when the vehicle 100 is traveling at a constant speed, on the images captured by the camera 10b, the images shown in FIGS.
The movement amount X1 shown in (b) and FIGS. 3 (b) to 3 (c).
It is different from the movement amount X2 shown in. That is, the vehicle 100
As the vehicle approaches the camera 10b, the apparent movement amount of the vehicle 100 existing in the image increases.

Therefore, if the imaging interval is determined with reference to the movement amount X1 when the vehicle 100 is present at a distance, the vehicle 10
The movement amount when 0 approaches the vicinity of the camera 10b may become too large. On the other hand, if the imaging interval is determined with reference to the movement amount X2 when the vehicle 100 is in the vicinity, the movement amount when the vehicle 100 is in the distance is small and it becomes difficult to detect the moving vehicle 100. The moving object detection apparatus according to the first embodiment detects a vehicle (hereinafter, referred to as a target vehicle) having the shortest distance from the host vehicle 1 among the vehicles approaching the host vehicle 1, and captures the captured image. The imaging interval is determined according to the position of the target vehicle above.

In FIGS. 3 (a)-(c), the vehicle 100 is
It appears as if it appears from the vanishing point (infinity point) of the road 110 located on the right side of the center of the figure and moves toward the left side of the figure. As described above, the traveling vehicle is the camera 10b.
3A to 3C, the apparent movement amount increases as the vehicle 100 moves to the left side of the image in FIG. 3A to FIG. 3C. That is, there is a correlation between the lateral position of the vehicle 100 on the image and the apparent movement amount.

FIG. 4 shows an image in the order of A, B, and C from the right.
It is the figure divided into one area. Further, a frame-out determination area (hatched portion) described later is provided at the leftmost end of the image. The moving object detection apparatus according to the first embodiment changes the interval at which the camera 10b takes an image, depending on which of the areas A, B, and C in FIG. 4 the target vehicle is in. Here, the imaging intervals when the target vehicle exists in the areas A, B, and C are T _A and T, respectively.
_{Let B} and T _C. The imaging interval is T _A when the target vehicle is not detected. In the case of the image captured by the camera 10b, the apparent movement amount increases as the target vehicle moves to the left side of the image. Therefore, the imaging interval T _A ,
The relationship between T _B and T _C is T _A > T _B > T _C.

FIG. 5A is a diagram showing the relationship between the lateral position in the image of the target vehicle and the apparent amount of movement. The lateral position in the image is based on the leftmost point of the image. FIG. 5A shows the results when the imaging intervals are set to constant intervals T _A , T _B , and T _C regardless of the position of the target vehicle. It can be seen from FIG. 5A that the apparent movement amount increases as the imaging interval increases, and the apparent movement amount increases as the target vehicle is located on the left side of the image.

FIG. 5B shows the lateral position and the apparent position in the image of the target vehicle when the imaging interval is changed according to the position of the target vehicle by using the moving body detecting apparatus according to the first embodiment. It is a figure which shows the relationship with the movement amount of. When the target vehicle is in the area A, the imaging interval is T _A , when it is in the area B, the imaging interval is T _B, and when it is in the area C, the imaging interval is T _C. As a result, FIG.
As shown in (b), it is possible to suppress the change in the apparent movement amount on the image regardless of the position of the target vehicle.

In FIG. 4, the frame-out determination area indicated by diagonal lines is provided for speedily performing the next target vehicle detection processing. That is, when the target vehicle approaches the frame-out determination area, it is determined that the target vehicle will be framed out from the captured image in the next processing cycle, and the imaging interval T is the maximum in the next processing cycle. _A is a new imaging interval,
The process of detecting the next target vehicle is performed. Accordingly, a moving vehicle that newly appears from the vanishing point direction of the road 110 shown in FIG. 4 can be detected quickly and reliably.

FIG. 6 is a flowchart showing the processing procedure of the target vehicle detection processing performed by the moving body detection apparatus according to the first embodiment. This processing is performed by the image processing ECU 20. In step S10, the interval at which the camera 10b images the right direction of the vehicle 1 is determined. The method of determining the imaging interval will be described later with reference to the flowchart shown in FIG. When the imaging interval is determined, the process proceeds to step S20.

In step S20, the camera 10b
The first image is captured. The captured image is an image processing EC
Captured by U20. In the next step S30, the second image is captured using the camera 10b at the image capturing interval determined in step S10. Image processing E for the captured image
When it is loaded into the CU 20, the process proceeds to step S40. In step S40, difference processing is performed using the two images acquired in step S20 and step S30 to extract a region in which the vehicle has moved (hereinafter referred to as a moving region). After performing the difference processing, the process proceeds to step S50.

In step S50, a moving vehicle is extracted based on the difference processing result obtained in step S40. The moving vehicle extraction processing will be described later with reference to the flowchart shown in FIG. When the moving vehicle is extracted, the process proceeds to step S60. In step S60, a target vehicle detection process is performed based on the mobile vehicle extracted in step S50. The target vehicle detection process will be described later with reference to the flowchart shown in FIG. After that, the processes of steps S10 to S60 described above are repeated.

FIG. 7 is a flow chart showing the detailed processing procedure of the imaging interval determination processing performed in step S10 of the flow chart shown in FIG. In step S110, the processing according to the flowchart shown in FIG. 6 (step S
In 10 to S60), an image of the target vehicle detected in the pre-processing cycle based on the detection processing result of the target vehicle performed in step S60 in the pre-processing cycle (the processing in the previous steps S10 to S60). Check the position above. When the process according to the flowchart shown in FIG. 6 is performed for the first time, it is assumed that the target vehicle does not exist.

In the next step S120, step S1
Based on the position confirmation result of the target vehicle performed in 10, it is determined whether the target vehicle does not exist or the target vehicle is approaching the flameout determination area. If it is determined that the target vehicle does not exist, or if it is determined that the frame-out determination area is approaching, the process proceeds to step S130, and otherwise, the process proceeds to step S140.

In step S130, the image capturing interval for acquiring the next image is set to T _A (initial image capturing interval), which has the longest image capturing interval. As a result, it is possible to quickly detect a vehicle that newly enters the imaging area. on the other hand,
In step S140, the imaging interval is determined based on the position of the target vehicle detected during the preprocessing cycle. For example, if the target vehicle detected during the preprocessing cycle is in the area B, the imaging interval is set to T _B ,
If it exists in the region C, the imaging time is set to T _C. When the imaging interval is determined in step S130 or S140, the process according to this flowchart ends.

FIG. 8 is a flow chart showing a detailed processing procedure of the moving vehicle extraction processing performed in step S50 of the flow chart shown in FIG. In step S200, the white line of the road is detected using the image before the inter-image difference process (step S40), that is, the image acquired in step S20 or step S30. The white line can be detected by a known method such as using the luminance information included in the image. When the white line of the road is detected, the process proceeds to step S210.

In step S210, step S200
The road area in the image is specified based on the white line detected in. When the road area is specified, the process proceeds to step S220. In step S220, the masking process is performed within the road region specified in step S210 on the image of the moving region extracted by the difference process performed in step S40 of the flowchart shown in FIG. The information of the moving area to be extracted is extracted. That is, the moving area existing outside the road area is removed. In the next step S230, labeling is performed on the moving area portion within the road area extracted in step S220, and each labeled area is extracted as an area in which the moving vehicle exists. That is, in step S230, moving vehicles existing in the road area (or plural moving vehicles when there are a plurality of them) are extracted. When the moving vehicle is extracted, the process according to this flowchart ends.

FIG. 9 is a flow chart showing a detailed processing procedure of the target vehicle detection processing performed in step S60 of the flow chart shown in FIG. Step S30
In 0, a process of associating the data in the pre-processing cycle with the data of the moving vehicle extracted in the current process (step S50 of the flowchart shown in FIG. 6) is performed. Specifically, based on the position of the moving vehicle on the image, the moving direction up to the previous processing, the size of the moving vehicle data, and the like, the moving vehicle detected during the preprocessing cycle and the current processing are extracted. Check if the moving vehicle is the same vehicle. When there are a plurality of extracted moving vehicles, it is confirmed whether or not they are the same vehicle for all the combinations. When data association processing is performed, step S
Proceed to 310.

In step S310, step S300
It is determined whether or not the same vehicle exists as a result of the associating process performed in. If it is determined that the same vehicle exists, the process proceeds to step S320, and if it is determined that the same vehicle does not exist, the process proceeds to step S370. In step S370, the moving vehicle detected in this processing is determined to be a newly detected vehicle, and the target vehicle detection processing ends.

In step S320, the moving direction of the moving vehicle determined to be the same vehicle is determined. When the moving direction is determined, the process proceeds to step S330. In step S330,
It is determined whether or not the moving direction determined in step S320 is a direction approaching the host vehicle 1. If it is determined that the vehicle 1 is approaching, the process proceeds to step S340, and if it is determined that the vehicle is moving away from the vehicle 1,
The process according to this flowchart ends.

In step S340, the horizontal position in the image is calculated for all the moving vehicles that are determined to be approaching the host vehicle 1, and the process proceeds to step S350. In step S350, the vehicle having the leftmost lateral position is specified from among the lateral positions of all the moving vehicles calculated in step S340. In the present embodiment, the camera 10b is used to detect a vehicle approaching from the right side in the traveling direction of the host vehicle 1 (see FIG. 3), and therefore the vehicle whose lateral position in the image is on the leftmost side is detected. Have been identified. In the moving body detection device of the present embodiment, it is possible to detect a vehicle approaching from the left side using the camera 10a, but in this case,
The vehicle whose lateral position is the rightmost will be specified. In the next step S360, the vehicle specified in step S350 is determined to be the target vehicle, and the process according to this flowchart ends.

According to the moving body detecting apparatus of the first embodiment, the image pickup interval is lengthened in the vicinity of the vehicle detected by the image processing if the vehicle detected by the image processing is present in the distance according to the position of the moving vehicle in the image. If it exists, the imaging interval is shortened. This imaging interval is predetermined according to the distance between the own vehicle and the moving vehicle so that the moving vehicle can be extracted from the two images picked up with a time difference. Accordingly, the moving vehicle can be reliably detected by changing the imaging interval. Further, when the moving vehicle approaches the frame-out determination area or when the moving vehicle is not detected, the imaging time is set to be the longest, so that a new moving vehicle can be detected quickly.

(Second Embodiment) When a vehicle approaching the host vehicle 1 is traveling at a constant speed, the moving object detecting device of the first embodiment is used to reliably move the vehicle. The vehicle can be detected. However, when the traveling speeds of the approaching vehicles are different, even if the imaging interval is changed according to the position of the moving vehicle in the image, it is not possible to make the moving amount in the image uniform. FIG. 10 shows the relationship between the lateral position of the vehicle in the image and the apparent movement amount when the traveling speeds of the approaching vehicles are different.

FIG. 10A shows that the imaging interval is constant (T _c ).
Shows the relationship between the lateral position of the vehicle in the image and the apparent movement amount, and the vehicle speed V of the vehicle shown by the solid line.
1 is smaller than the vehicle speed V2 of the vehicle shown by the dotted line.
Therefore, even if the lateral position on the image of the vehicle and the lateral position on the image of the vehicle are the same, the apparent movement amount on the image is different, and the apparent movement amount of the vehicle is the apparent movement amount of the vehicle. Will be larger than.

FIG. 10B shows the relationship between the lateral position of the vehicle in the image and the apparent amount of movement when the moving object detecting apparatus according to the first embodiment is used. As shown in FIG. 10B, when the moving speed is high like a vehicle,
Even if the imaging interval is changed according to the position of the moving vehicle in the image,
The difference in the amount of movement on the image becomes large. In the moving body detection device of the second embodiment, the moving speed of the moving vehicle detected by the image processing is calculated, and the imaging interval is set according to the calculated moving speed. As a result, even if the moving speeds of the moving vehicles are different, it is possible to reduce the difference in the apparent moving amount on the image.

The structure of the moving body detecting apparatus according to the second embodiment is the same as the structure of the moving body detecting apparatus according to the first embodiment shown in FIG. Also, camera 1
The processing method (flowchart in FIG. 6) of performing the difference processing on the two images captured at 0b to extract the moving vehicle and specify the target vehicle is also the same as that of the moving object detection apparatus according to the first embodiment. Is. In the moving body detection device according to the second embodiment, among the processes according to the flowchart shown in FIG.
The processing content for determining the imaging interval in step S10 is the first
This is different from the moving body detection device of the embodiment.

FIG. 11 is a flow chart showing the detailed processing procedure of processing for determining the interval at which two images are picked up by the camera 10b. The same processes as the processes according to the flowchart shown in FIG. 7, which are performed by the moving body detection device according to the first embodiment, are designated by the same reference numerals, and different processes will be mainly described. In step S110, the position on the image of the target vehicle detected in the pretreatment cycle is confirmed based on the detection processing result of the target vehicle in the pretreatment cycle, and the process proceeds to step S120.

In step S120, step S110
Based on the result of the target vehicle position confirmation performed in
It is determined whether the target vehicle does not exist or the target vehicle is approaching the flameout determination area. Is it determined that the target vehicle does not exist,
Alternatively, if it is determined that the frame-out determination area is approaching, the process proceeds to step S130, and otherwise, the process proceeds to step S400. In step S130,
Next, the image capturing interval for acquiring an image is set to T _A (initial image capturing interval), which has the longest image capturing interval, and the processing according to this flowchart ends.

In step S400, the amount of movement of the target vehicle in the image is calculated based on the two images (steps S20 and S30 in the flowchart of FIG. 6) taken during the preprocessing cycle. When the amount of movement of the target vehicle in the image is calculated, the process proceeds to step S410. In step S410, based on the movement amount calculated in step S400 and the interval at which two images are captured,
The moving speed in the image of the target vehicle is calculated.
When the moving speed in the image of the target vehicle is calculated, the process proceeds to step S420.

In step S420, step S410.
The imaging interval is calculated based on the moving speed calculated in.
In order to make the amount of movement of the target vehicle uniform in the image, the imaging interval is made smaller as the moving speed in the image becomes higher, and the imaging interval becomes longer as the moving speed becomes smaller. The imaging interval can be calculated, for example, by preparing in advance a table that defines the relationship between the moving speed of the moving vehicle in the image and the imaging interval, and using the moving speed calculated in step S410 and this table. Alternatively, the reference moving speed may be set in advance, and the imaging interval may be calculated based on the difference between the moving speed calculated in step S410 and the reference speed.

As described above, according to the moving object detecting apparatus of the second embodiment, the image pickup interval is determined according to the moving speed on the image of the vehicle approaching the own vehicle. Even if the position on the image is different, the moving vehicle can be accurately detected.

The present invention is not limited to the above-mentioned embodiment. For example, in the first embodiment, the region in the image is divided into three and three types of imaging intervals are used, but the region in the image is divided into four or more regions and four or more types of imaging intervals are used. This makes it possible to further equalize the apparent movement amount of the moving vehicle on the image. Further, in the above-described embodiment, the case where the vehicle approaching the own vehicle is detected has been described, but the present invention can also be applied to a device that recognizes a vehicle moving away from the own vehicle.

Further, the moving body on which the moving body detecting apparatus according to the present invention is mounted is not limited to a vehicle, but can be applied to a two-wheeled vehicle or the like. The moving body detected by the moving body detection device is not limited to the vehicle, and moving bodies such as people and bicycles can be detected.

Further, in the second embodiment, the image pickup interval is determined according to the moving speed on the image of the vehicle approaching the host vehicle. However, the moving amount calculated in step S400 of the flowchart shown in FIG. It is also possible to perform feedback control so that is constant. That is, step S
If the movement amount calculated in 400 is large, the next imaging time is shortened to reduce the movement amount, and if the movement amount is small, the next imaging time is lengthened to increase the movement amount. This makes it possible to reliably detect the moving vehicle regardless of the position of the moving vehicle on the image and the moving speed.

Correspondence between the constituent elements of the claims and the constituent elements of one embodiment is as follows. That is,
The front and side cameras 10a and 10b serve as image pickup means and perform image processing E.
The CU 20 constitutes a moving body detecting means, a time setting means, and a moving amount detecting means, respectively. Note that each component is not limited to the above configuration as long as the characteristic function of the present invention is not impaired.

[Brief description of drawings]

FIG. 1 is a diagram showing a configuration of a first embodiment of a moving object detection device according to the present invention.

FIG. 2 is a diagram showing a position where a front side camera is mounted on a vehicle.

FIG. 3 is a diagram showing images taken at regular time intervals.

FIG. 4 is a diagram showing an area and a frame-out determination area when an image is divided into three parts.

FIG. 5 is a diagram showing a relationship between a lateral position in an image of a target vehicle and an apparent movement amount, wherein FIG. 5 (a) shows a case where an imaging interval is constant and FIG. Diagram when the imaging interval is changed

FIG. 6 is a flowchart showing a processing procedure for detecting a target vehicle by using the moving body detection device according to the first embodiment.

FIG. 7 is a flowchart showing a processing procedure for determining an imaging interval.

FIG. 8 is a flowchart showing a processing procedure for extracting a moving vehicle.

FIG. 9 is a flowchart showing a processing procedure for determining a target vehicle.

FIG. 10 is a diagram showing the relationship between the lateral position of the vehicle in the image and the apparent movement amount when the traveling speeds of the approaching vehicles are different, and FIG. Illustration of
FIG. 10B is a diagram when the imaging interval is changed according to the position in the image.

FIG. 11 is a block diagram of the moving body detection device according to the second embodiment.
Flowchart showing the processing procedure for determining the imaging interval

[Explanation of symbols]

1 ... Own vehicle, 10a ... Front side camera (left), 10b ... Front side camera (right), 20 ... Image processing ECU, 30 ... Warning ECU, 40 ... Vehicle speed sensor, 50 ... Warning indicator, 60 ... Warning buzzer , 70 ... In-vehicle monitor, 100 ...
Approaching vehicle, 110 ... Road

   ─────────────────────────────────────────────────── ─── Continued front page    F term (reference) 5B057 AA16 BA02 DA07 DA08 DB02                       DC14 DC32                 5C054 CH02 FC01 FC12 FC14 HA30                 5H180 AA01 CC04 LL04 LL07 LL08                       LL15                 5L096 BA04 CA02 DA03 FA03 FA66                       GA08 HA04

Claims (6)

[Claims] 1. An image pickup unit installed on a moving body for picking up an image of a predetermined range, a first image picked up by the image pickup unit, and an image picked up after a lapse of a predetermined time from the time when the first image was picked up. The moving body detecting means for detecting another moving body that is relatively displaced with respect to the moving body based on the difference processing result with the second image, and the distance between the other moving body and the moving body is short. The moving object detection device further comprises a time setting means for shortening the predetermined time. 2. The moving body detection device according to claim 1, wherein the time setting unit is configured to detect the other moving body in one of the first image and the second image. A moving body detection device, wherein a distance between the other moving body and the moving body is determined based on a position in the lateral direction. 3. The moving body detecting apparatus according to claim 1, wherein the moving body detects a moving amount of the other moving body in the image based on the first image and the second image. The moving body detecting device further comprising an amount detecting means, wherein the time setting means sets the predetermined time so that the moving amount detected by the moving amount detecting means becomes constant. 4. A first image picked up by an image pick-up means installed on a moving body and picking up an image of a predetermined range, and a second image picked up after a lapse of a predetermined time from the time when the first image was picked up.
On the basis of the difference processing result with the image of, a moving body detection method for detecting another moving body that is relatively displaced with respect to the moving body, the closer the distance between the other moving body and the moving body, the more A method of detecting a moving object, characterized by shortening a predetermined time. 5. The moving object detection method according to claim 4, wherein the distance between the other moving object and the moving object is one of the first image and the second image. A moving object detection method, characterized in that it is determined based on a lateral position of the other moving object in the inside. 6. The moving body detection method according to claim 4, wherein the moving amount of the other moving body in the image is detected based on the first image and the second image, The moving body detection method, wherein the predetermined time is set so that the detected moving amount of the other moving body becomes constant.