JP2004201067A - Vehicle side image monitoring apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect a moving object which has arrived within a close range of an intersection. <P>SOLUTION: In an image picked up by a camera 1a, 1b for imaging sides of a vehicle 10, a region where a near vehicle is searched is set to search a vehicle 20 within a close range of the vehicle 10 so that the vehicle 20 within the close range is searched on the basis of a pattern of an image density histogram within the range where the near vehicle is searched. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a vehicle side monitoring device that monitors a moving body approaching from a side road when entering a left or right intersection with poor visibility.
[0002]
[Prior art]
Conventionally, there is a device that detects a vehicle approaching an intersection from a side road based on an image captured by an on-board camera that captures a side of the vehicle when the vehicle enters an intersection or the like with poor visibility to the left and right. It is known (see Patent Document 1). In this conventional device, an optical flow is extracted based on two images taken at a predetermined time interval by a vehicle-mounted camera, and an approaching degree of an approaching vehicle is determined based on the magnitude of the extracted optical flow. Warning the driver of the vehicle.
[0003]
[Patent Document 1]
JP 2001-213254 A
[0004]
[Problems to be solved by the invention]
However, in the conventional device, if the approaching vehicle has reached the closest distance of the intersection, the approaching vehicle will be out of the shooting range even if an attempt is made to take a second image after a predetermined time, and the optical flow will be interrupted. There is a possibility that the detection process cannot be performed.
[0005]
The present invention provides a vehicle side monitoring device that can detect a moving object even when the moving object has reached a short distance from an intersection.
[0006]
[Means for Solving the Problems]
A vehicle side monitoring device according to the present invention includes: an imaging unit that captures at least one of a left side and a right side of a host vehicle; and a host vehicle on a side road based on one image captured by the imaging unit. Moving object detecting means for detecting a moving object existing within a predetermined distance from the moving object.
[0007]
【The invention's effect】
According to the vehicle side monitoring device according to the present invention, it is possible to detect a moving body that has reached the closest distance of the vehicle on the side road based on one image captured by the imaging unit.
[0008]
BEST MODE FOR CARRYING OUT THE INVENTION
The vehicle side monitoring device according to the present embodiment includes a camera for photographing the side of the vehicle, and performs image processing described below on the image photographed by the camera, so that the vehicle approaching from the side of the own vehicle. And other moving objects are detected. As shown in FIG. 1, one camera 1a, 1b for photographing the side of the vehicle is installed on each of the left and right sides of the front side of the vehicle 10. The camera 1a captures an image of the right side in the vehicle traveling direction, and the camera 1b captures an image of the left side in the vehicle traveling direction.
[0009]
FIG. 2 is a diagram showing a configuration of an embodiment of a vehicle side monitoring device according to the present invention. The vehicle side monitoring device according to one embodiment includes two CCD cameras 1a and 1b, an image processing controller 3, a video control device 4, a display 5, a navigation device 6, a vehicle speed sensor 7, and a buzzer 8. And a side monitor switch 9.
[0010]
Images captured by the CCD cameras 1a and 1b installed on the left and right sides of the front side of the vehicle 10 are sent to the image processing controller 3 as video signals Sa and Sb. The image processing controller 3 executes filtering processing, various arithmetic processing, and the like on the video signals Sa and Sb in pixel units. Further, the image processing controller 3 controls the video signal S1 based on the image captured by one of the CCD cameras 1a and 1b, or the video signal S1 obtained by synthesizing the images captured by both cameras 1a and 1b. Is output to the video control device 4. Further, the image processing controller 3 outputs necessary information to the video control device 4 as a notification signal Sd based on the result of performing the image processing on the video signals Sa and Sb.
[0011]
The navigation device 6 has a function of detecting the position of the own vehicle using a GPS or the like, and a function of searching for a route from the current position of the own vehicle to the destination. The vehicle position information and the guidance route information to the destination detected by the navigation device 6 are input to the video control device 4 as a video signal Sn. The video control device 4 includes so-called navigation information such as the position of the vehicle detected by the navigation device 6, a map around the vehicle, and a guidance route, a display for controlling an audio function, and a vehicle captured by the CCD cameras 1a and 1b. It has a function to control the display of various information such as the display of surrounding images. The video control device 4 outputs to the image processing controller 3 a control signal Sc for switching an image output from the image processing controller 3 and instructing execution of image processing. Further, it outputs a video signal S2 to be displayed on the display 5 to the display 5.
[0012]
The display 5 is provided at a position in the vehicle cabin where the driver can view it, and displays navigation information and images captured by the CCD cameras 1a and 1b based on the image signal S2 input from the image control device 4. The vehicle speed sensor 7 measures the rotation speed of the wheels of the own vehicle and outputs a pulse signal proportional to the detected rotation speed to the video control device 4. The buzzer 8 emits an alarm sound when a driver needs to be warned, for example, when a vehicle approaching the host vehicle is detected by a method described later.
[0013]
The side monitor switch 9 activates a program for switching and displaying a video taken by the CCD cameras 1a and 1b with a navigation display, and for detecting a vehicle approaching from the side based on the captured image information. And operated by a driver or the like. When a condition described later is satisfied when the side monitor switch 9 is on, the image processing controller 3 performs side vehicle detection control. Further, when the side detection switch 9 is off, the side vehicle detection control is not performed even if a condition described later is satisfied.
[0014]
FIG. 3 is a diagram illustrating an internal configuration of the image processing controller 3. The image processing controller 3 includes a decoder 3a, an image processing IC 3b, an encoder 3c, an image memory 3d, a ROM 3e, and an image processing control CPU 3f. Video signals Sa and Sb output from the CCD cameras 1a and 1b are input to a decoder 3a. The decoder 3a converts the input video signals Sa and Sb into digital data and outputs the digital data to the image processing IC 3b. The image processing IC 3b executes various arithmetic processing on the image data on which the A / D conversion processing has been performed. The processed image data is output to the encoder 3c. The encoder 3c performs a D / A conversion process on the processed image data. The video signal S1 after the D / A conversion processing is performed is output to the video control device 4.
[0015]
The above-described image processing IC 3b, the image memory 3d, the ROM 3e, and the image processing control CPU 3f are connected by a common bus. The image memory 3d can temporarily store input image data and data being processed. The image memory 3d has a predetermined capacity for storing a plurality of images required for processing. The ROM 3e stores an image processing program such as a program for detecting a vehicle approaching the host vehicle based on images captured by the CCD cameras 1a and 1b. The image processing control CPU 3f controls the timing of performing image processing and the input / output of various signals based on the control signal Sc transmitted from the video control device 4.
[0016]
FIG. 4 is an embodiment showing a control procedure for detecting a vehicle approaching from the side by using the cameras 1a and 1b when, for example, the host vehicle 10 approaches a T road or an intersection with poor visibility. It is a flowchart of a form. This control is performed by the image processing dedicated IC 3 b and the image control device 4 provided in the image processing controller 3. The control starting from step S10 starts when an ignition switch (not shown) is turned on. In the following description, it is assumed that an approaching vehicle is detected based on an image captured by the camera 1a.
[0017]
In step S10, based on the video signal Sn input from the navigation device 6 to the video control device 4, information such as map information or vehicle position information selected by the video control device 4 is displayed on the display 5 in the navigation information. indicate. That is, when the driver or the like operates an operation button (not shown), information requested to be displayed by the driver or the like is selected by the video control device 4 and displayed on the display 5. When the information selected by the video control device 4 is displayed on the display 5, the process proceeds to step S20.
[0018]
In step S20, the image control device 4 calculates the vehicle speed of the host vehicle based on the pulse input from the vehicle speed sensor 7, and determines whether the calculated vehicle speed is equal to or less than a predetermined value. This predetermined value is a condition value for continuously displaying the navigation screen displayed on the display 5 in step S10, and is set to 10 km / h in the present embodiment. If it is determined that the vehicle speed is equal to or lower than the predetermined value, the process proceeds to step S30. If it is determined that the vehicle speed is higher than the predetermined value, the process returns to step S10, and the navigation screen is continuously displayed on the display 5.
[0019]
In step S30, it is determined whether or not the side monitor switch 9 is turned on based on a signal input from the side monitor switch 9 to the video control device 4. If it is determined that the side monitor switch 9 is on, the process proceeds to step S40. If it is not on, the display of a captured image at an intersection or the like and the process of detecting an approaching vehicle are determined to be unnecessary, and the process returns to step S10.
[0020]
In step S40, the image taken by the camera 1a is displayed on the display 5. That is, the image processing controller 3 outputs the video signal S1 based on the video signal Sa input from the camera 1a to the video control device 4. The video control device 4 switches from the output video signal Sn of the navigation device 6 to the video signal S1 output from the image processing controller 3 as the video signal S2 output to the display 5. As a result, a side image of the vehicle 10 captured by the camera 1a is displayed on the display 5.
[0021]
In step S50 following step S40, the image control device 4 calculates the vehicle speed of the own vehicle again based on the pulse input from the vehicle speed sensor 7, and determines whether or not the calculated vehicle speed has become 0. If it is determined that the vehicle speed is 0 and the vehicle has stopped (temporarily stopped) at an intersection or the like, the process proceeds to step S60, and if it is determined that the vehicle speed is not 0, the process returns to step S20.
[0022]
In step S60, the image Tn captured by the camera 1a is stored in the image memory 3d in the image processing controller 3, and the process proceeds to step S70. In step S70, based on the image data Image Tn stored in the image memory 3d in step S60, a process of detecting a moving object such as a vehicle located at a short distance from the own vehicle is performed. In the present embodiment, a range within a predetermined distance from the host vehicle is referred to as a close distance. The details of the close range vehicle detection processing will be described with reference to the flowchart shown in FIG.
[0023]
In step S200 of the flowchart shown in FIG. 5, a search area for a close-range vehicle is set in a predetermined area of the image data Image Tn. Here, a rectangular area having an appropriate area at a position where the approaching vehicle is expected to disappear from the captured image is set as a search area based on the mounting positions of the cameras 1a and 1b and the photographing range. FIG. 6A is an image captured by the camera 1a in the situation shown in FIG. 1, and an area surrounded by a frame line in FIG. 6A is a close-range vehicle search area. Note that the frame lines indicating the search area are shown for explanation, and are not actually displayed on the display 5.
[0024]
In step S210, an image density histogram is created in the close range vehicle search area set in step S200. The image photographed by the camera 1a and input to the video control device 4 is a monochrome image of 256 gradations (8 bits), and black is represented by density 0 and white is represented by density 255. The density histogram is obtained by plotting the density value on the horizontal axis and the frequency of appearance of the density on the vertical axis. For example, the image density histogram in the close-range vehicle search area of the video shown in FIG. The result is as shown in FIG. After creating the density histogram, the process proceeds to step S220.
[0025]
In step S220, the pattern of the density histogram created in step S210 is analyzed. As shown in FIG. 6A, when a vehicle is reflected in the search area, the density of various parts of the vehicle body is reflected. Therefore, the density histogram is black as shown in FIG. 6B. It is widely distributed from a density close to (density value 0) to a density close to white (density value 255). As shown in FIG. 7, when a white road surface paint display such as a stop line is displayed on the road, a white line may appear in the search area as shown in FIG. 8A. In the density histogram in this case, as shown in FIG. 8B, a peak of the density value appears in a darker density portion of the road surface portion and a brighter density portion of the white line portion. FIG. 9A is an image in a case where only the road surface is shown in the search area. In this case, the density histogram has a sharp peak in the density of the road surface portion as shown in FIG. 9B. I do.
[0026]
As shown in FIGS. 6 (b), 8 (b), and 9 (b), the density distribution in the close range vehicle search area is characterized by the presence and absence of vehicles in the search area. Are different. That is, when a vehicle is present in the search area, the image density is widely distributed as shown in FIG. 6B, so that no sharp peak of the density value exists. As shown in FIGS. 8B and 9B, there are sharp peaks. The presence or absence of a sharp peak in the density value can be detected, for example, by performing differentiation in the density value direction (horizontal axis direction) of the density histogram and detecting the presence or absence of a sharp change in the density value.
[0027]
In step S230, as a result of the analysis of the density histogram performed in step S220, it is determined whether or not there is a sharp peak in the density value. If it is determined that there is a sharp peak in the density value, no vehicle exists in the close range vehicle search area, and there is no need to issue a warning or the like to the own vehicle. It proceeds to step S80 of the flowchart shown in FIG. On the other hand, if it is determined that there is no sharp peak in the density value, the process proceeds to step S240. In step S240, a warning is issued to the driver of the host vehicle that the vehicle is approaching a close distance of the host vehicle. As shown in FIG. 10, the warning is issued by displaying a call for attention on a part of the display screen of the display 5 or by outputting an alarm sound from the buzzer 8. When a warning is issued to the driver of the host vehicle, the close range vehicle detection process ends, and the process proceeds to step S80 in the flowchart shown in FIG.
[0028]
In step S80 of the flowchart shown in FIG. 4, the image data Image Tn + 1 at the timing of Tn + ΔT after ΔT seconds from the timing Tn at which the photographed image data Image Tn was stored in the image memory 3d in step S60 is stored in the image memory 3d. FIG. 11 is a diagram illustrating a state of the vehicle 20 approaching the host vehicle 10 that has been temporarily stopped before entering the intersection. FIG. 12A shows an image shot by the camera 1a at the time Tn, and FIG. 12B shows an image shot at the time Tn + ΔT. In step S90 following step S80, the presence or absence of a vehicle approaching the host vehicle is detected. This approaching vehicle detection process is for detecting an approaching vehicle that cannot be detected by the close range vehicle detection process performed in step S70, and the content of the process will be described with reference to the flowchart shown in FIG.
[0029]
In step S300 of the flowchart shown in FIG. 13, two images of the image data Image Tn acquired in step S60 of the flowchart shown in FIG. 4 and the image data Image Tn + 1 acquired in step S80 with a difference of ΔT seconds. Using the data, an optical flow is detected. The optical flow is a velocity vector relating to the apparent movement of each point in the captured image, which is generated with the relative movement of a moving body such as the vehicle 20 moving relatively to the camera 1a. A detailed description is omitted because the optical flow detection method is publicly known, but, for example, regarding the pixel data in a predetermined block area of the image Image Tn, the image Image Tn has a large correlation value in the image Tn + 1 after ΔT seconds It is possible to calculate whether or not an area exists, and detect the amount of movement between the area and the area where a large correlation value is observed. FIG. 12C is a diagram showing an example of an optical flow detected based on the image shown in FIG. 12A and the image shown in FIG.
[0030]
When the optical flow detection process is performed in step S300, the process proceeds to step S310. In step S310, it is determined based on the result of the optical flow detection processing performed in step S300 whether an optical flow in a direction approaching the vehicle 10 (hereinafter, referred to as an approach flow) is detected. In the present embodiment, since the description is made using the video taken by the camera 1a, the approach flow flows from the right to the left of the image. If it is determined that the approach flow as shown in FIG. 12C has been detected, the process proceeds to step S320. If it is determined that the approach flow has not been detected, the approaching vehicle detection process ends, and the process proceeds to step S100 in the flowchart shown in FIG.
[0031]
In step S320, since there is a vehicle approaching the host vehicle 10, a determination process is performed to determine whether it is necessary to issue a warning to the driver of the host vehicle 10. The necessity of the warning is determined based on the size of the optical flow. The optical flow increases as the speed of the vehicle 20 approaching the host vehicle 10 increases, and increases as the approaching vehicle 20 approaches the host vehicle 10. Therefore, the presence or absence of a warning is determined based on the size of the detected optical flow and the size of a predetermined threshold value set in advance.
[0032]
In step S330 subsequent to step S320, it is determined whether or not a warning is necessary based on the result of the processing for determining whether or not there is a warning performed in step S320. When the magnitude of the detected optical flow is larger than the predetermined threshold, it is determined that a warning to the driver is necessary, and the process proceeds to step S340, and when the optical flow is equal to or smaller than the predetermined threshold. , It is determined that there is no need to issue a warning, the approaching vehicle detection process ends, and the routine proceeds to step S100 in the flowchart shown in FIG.
[0033]
In step S340, the driver of the host vehicle 10 is warned that the vehicle is approaching the host vehicle 10. The warning is performed by, as shown in FIG. 14, displaying a call for attention on a part of the display screen of the display 5 or outputting an alarm sound from the buzzer 8. When a warning is issued to the driver of the host vehicle, the approaching vehicle detection process ends, and the process proceeds to step S100 in the flowchart shown in FIG.
[0034]
In step S100, the image control device 4 calculates the vehicle speed of the own vehicle based on the pulse input from the vehicle speed sensor 7, and determines whether the calculated vehicle speed is equal to or higher than a predetermined value. This predetermined value is, for example, 10 km / h as in step S20. If the vehicle speed of the host vehicle is equal to or higher than the predetermined value, that is, if the host vehicle has entered an intersection or the like and has resumed traveling, the process returns to step S10, and the navigation display is performed on the display 5 again. On the other hand, if it is determined that the vehicle speed of the host vehicle is lower than the predetermined value, the process proceeds to step S110.
[0035]
In step S110, it is determined whether or not the side monitor switch 9 is continuously turned on. If it is determined to be on, the process returns to step S80, and the approaching vehicle detection process is performed again. That is, the image data Image Tn + 2 that is ΔT seconds after the image data Image Tn + 1 stored in the image memory 3d in the previous process of step S80 is acquired, and the approaching vehicle detection process is performed based on the two image data. . On the other hand, when it is determined that the side monitor switch 9 is turned off, the process returns to step S10, and the navigation display is performed again on the display 5.
[0036]
As described above, according to the vehicle side monitoring device in the present embodiment, based on one image captured by the cameras 1a and 1b, the vehicle on the side road intersecting the road on which the vehicle runs. , That is, a moving object existing within a range of a predetermined distance can be detected. Therefore, it is possible to detect a moving object at a short distance that cannot be detected by a method of extracting an optical flow using two images captured with a time difference. Further, the method of acquiring two images with a time difference has a problem that a warning to a driver is delayed even when a moving object such as a vehicle can be detected. The device detects a short-distance vehicle based on one image, so that a warning can be promptly given to the driver.
[0037]
Upon detecting a moving object, a vehicle search area for detecting a moving object existing within a predetermined distance from the host vehicle is set in one image captured by the cameras 1a and 1b, and an image in the search area is set. Since the moving object is detected based on the information regarding the concentration, the moving object existing within a predetermined distance from the host vehicle can be reliably detected. Further, the information on the image density is the image density distribution in the vehicle search area, and the moving object is detected based on the image density distribution, so that the moving object existing within a predetermined distance from the own vehicle can be more reliably detected. It can be detected reliably.
[0038]
When the moving object is present in the vehicle search area of the captured image, since there is no sharp peak in the image density distribution, based on whether there is a sharp peak in the image density distribution, It is possible to reliably detect a moving object existing within a predetermined distance from the own vehicle.
[0039]
After detecting a moving object within a predetermined distance range (closest distance) from the vehicle, the vehicle approaches the vehicle based on at least two images captured at predetermined time intervals by the cameras 1a and 1b. Since a moving object is detected, it is possible to detect a moving object existing at a position longer than a predetermined distance. At this time, the optical flow is detected based on the two images, and a warning is issued to the driver when the magnitude of the optical flow is larger than a predetermined value. Only the body can be notified by a warning. That is, it is possible to prevent the driver from being warned based on the detection of a moving object having a low risk for the own vehicle.
[0040]
The present invention is not limited to the above embodiment. For example, as shown in FIGS. 6 (a), 8 (a) and 9 (a), a short range vehicle search area set in a predetermined area of an image captured by the cameras 1a and 1b is a rectangular area. did. However, as shown in FIG. 15, a trapezoidal area may be used. In step S70 of the flowchart shown in FIG. 4, a short-range vehicle detection process is performed by setting a rectangular area at a position assumed to be a road area based on the mounting positions of the cameras 1a and 1b and the photographing range. . The method for setting the close-range vehicle search area is based on the premise that the road where the vehicle is located and the intersection road are on the same horizontal plane, and the width of the intersection road is constant. However, if the crossing road has a large gradient with respect to the road where the vehicle is located, or if the width of the crossing road is extremely wide or narrow, the vehicle search area is uniquely different from the captured image. Is set, there is a possibility that a portion other than the road surface portion is included in the search area. In this case, if a portion other than the road surface portion, for example, a background portion is included in the search region, it becomes difficult to analyze the density histogram in the search region. Therefore, it is desirable to set the search area so as not to include the background area.
[0041]
A method for setting the search area shown in FIG. 15 will be described. A straight line is detected by a method such as Hough transform using image data Image Tn photographed after the own vehicle is temporarily stopped at an intersection or the like, and a boundary between a road and a portion other than the road is extracted. When an image captured by the camera 1a is used, a search is made for an area surrounded by a boundary on the far side of the extracted road (an upper boundary on the image) and a left frame and a lower frame of the image. Set to area. If the search area is set by such a method, an area other than the road surface portion is not included in the search area, so that the detection accuracy of the moving object can be improved.
[0042]
The cameras for capturing the images of the side of the vehicle are provided one by one on the left and right sides of the front of the vehicle 10, but may be mounted on the left and right of the rear part of the vehicle 10. This case is effective, for example, when entering a road while retreating from a garage or a parking lot. Further, the angle of view of the cameras 1a and 1b can be freely set, for example, wide angle according to the surrounding monitoring situation. Further, an image obtained by synthesizing the left and right images of the vehicle 10 using a prism or a mirror may be taken by one camera. In this case, it is necessary to adjust the set position of the short-range vehicle search area according to the obtained image.
[0043]
What is detected by the vehicle side monitoring device according to the present invention is not limited to the vehicle, but may be a motorcycle or a pedestrian.
[0044]
The correspondence between the components of the claims and the components of the embodiment is as follows. That is, the cameras 1a and 1b are imaging means, the image processing controller 3 is a first moving object detecting means, a search area setting means, an image density distribution creating means, a line detecting means and a second moving object detecting means, and the buzzer 8 And the display 5 constitute alarm means. Note that each component is not limited to the above configuration as long as the characteristic functions of the present invention are not impaired.
[Brief description of the drawings]
FIG. 1 is a diagram showing a mounting position and a photographing range of a camera.
FIG. 2 is a diagram showing a configuration of an embodiment of a vehicle side monitoring device according to the present invention;
FIG. 3 is a diagram showing a detailed configuration of an embodiment of an image processing controller.
FIG. 4 is a flowchart of an embodiment showing processing contents performed by the vehicle side monitoring device according to the present invention;
FIG. 5 is a flowchart of an embodiment showing details of a close-range vehicle detection process.
6A is a diagram showing an image photographed under the situation shown in FIG. 1, and FIG. 6B is a density histogram created based on the photographed image of FIG. 6A.
FIG. 7 is a diagram showing a state where a road surface such as a white line is displayed on the road surface;
8A is a diagram showing an image photographed under the situation shown in FIG. 7, and FIG. 8B is a density histogram created based on the photographed image in FIG. 8A.
9A is a diagram illustrating an example of an image captured when no approaching vehicle, white line, or the like exists, and FIG. 9B is created based on the captured image in FIG. 9A; Density histogram
FIG. 10 is a diagram showing an example of a warning display.
FIG. 11 is a diagram showing a state of a vehicle approaching a host vehicle that is temporarily stopped before entering an intersection;
12A is a diagram illustrating an image captured at time Tn, FIG. 12B is a diagram illustrating an image captured at time Tn + ΔT, and FIG. FIG. 12 is a diagram showing an example of an optical flow detected based on the images shown in FIGS.
FIG. 13 is a flowchart illustrating an example of an approaching vehicle detection process according to an embodiment;
FIG. 14 is a diagram showing an example of a warning display when giving a warning that a vehicle approaching the host vehicle exists;
FIG. 15 is a diagram showing a close-range vehicle search area of a trapezoid.
[Explanation of symbols]
1a, 1b: CCD camera, 3: Image controller, 3a: Decoder, 3b: Image processing dedicated IC, 3c: Encoder, 3d: Image memory, 3e: ROM, 3f: Image processing control CPU, 4: Video control device, 5 ... display, 6 ... navigation device, 7 ... vehicle speed sensor, 8 ... buzzer, 9 ... side monitor switch, 10 ... own vehicle, 20 ... approaching vehicle

Claims (10)

Imaging means for imaging at least one of the left side and the right side of the vehicle,
A first moving object detecting unit that detects a moving object existing within a predetermined distance from the host vehicle on a side road based on one image picked up by the image pickup unit. Vehicle side monitoring device. The vehicle side monitoring device according to claim 1,
In one image picked up by the image pickup means, further comprising a search area setting means for setting a vehicle search area for detecting a moving object existing within a predetermined distance from the own vehicle,
The vehicle side monitoring device according to claim 1, wherein the first moving body detecting means detects the moving body based on information about an image density in a search area set by the search area setting means. The vehicle side monitoring device according to claim 2,
Image density distribution creating means for creating an image density distribution in the search area set by the search area setting means,
The vehicle side monitoring device according to claim 1, wherein the first moving body detecting means detects the moving body based on an image density distribution created by the image density distribution creating means. The vehicle side monitoring device according to claim 3,
The first moving object detecting means detects that the moving object is within a predetermined distance from the host vehicle when there is no sharp density value peak in the image density distribution created by the image density distribution creating means. A vehicle side monitoring device that determines that the vehicle exists. The vehicle side monitoring device according to claim 3,
The first moving object detecting means detects that the moving object is within a predetermined distance from the host vehicle when a sharp density value peak exists in the image density distribution created by the image density distribution creating means. A vehicle side monitoring device that determines that the vehicle does not exist. The vehicle side monitoring device according to any one of claims 2 to 5,
The vehicle side monitoring device, wherein the search area setting means sets the search area based on information on at least one of an attachment position of the imaging means with respect to a host vehicle and an imaging range of the imaging means. . The vehicle side monitoring device according to any one of claims 2 to 6,
The image capturing apparatus further includes a line detecting unit that detects a line indicating an edge of a road in the image captured by the image capturing unit,
The vehicle side monitoring device according to claim 1, wherein the search area setting means sets the search area in a road area in the captured image based on the line detected by the line detection means. The vehicle side monitoring device according to any one of claims 1 to 7,
After the moving object detection processing by the first moving object detecting means, a second detecting means detects a moving object approaching the own vehicle based on at least two images picked up by the image pickup means at predetermined time intervals. A vehicle side monitoring device, further comprising a moving body detection unit. The vehicle side monitoring device according to any one of claims 1 to 8,
A vehicle side monitoring device, further comprising an alarm unit that issues an alarm to at least a driver of the own vehicle when a moving object is detected by the first moving object detection unit. The vehicle side monitoring device according to claim 8,
The second moving body detection means detects a moving body approaching the own vehicle by detecting an optical flow based on the at least two images,
A vehicle side monitoring device, further comprising an alarm unit for issuing an alarm to at least a driver of the own vehicle when the magnitude of the optical flow detected by the second mobile unit detection unit is larger than a predetermined value. .

Images