JP2002099908A - Detection of approaching vehicle, and image processing device detecting vehicle lane position - Google Patents

Abstract

PROBLEM TO BE SOLVED: To realize an image processing device, enabling both of detection of a lane position and monitoring of a vehicle or the like approaching a blind spot area in each of the left and right directions, even when it approaches close to a vehicle ahead. SOLUTION: Two photographing parts, each having a photographing area ranging by 150 degrees in the horizontal direction and ranging by 60 degrees in the vertical direction, are arranged on both left and right sides of the front part of an own vehicle 10. The extension in the photographing depth direction of a central point of each of the photographing areas of the photographing parts 1 and 2 is set at an inclination of 45 degrees to the advancing direction of the own vehicle 10, with respect to the horizontal direction of the vehicle 10, and each of the photographing areas of the photographing parts 1 and 2 is an area limited by a boundary extending from the photographing part and tilting at 30 degrees toward the central axis direction of the vehicle 10 from the vehicle 10 advancing direction and a boundary extending from the photographing part and tilting backward at 30 degrees from the line at right angle from the vehicle 10 advancing direction. The extension in the photographing depth direction is set tilted downward by 3 degrees, with respect to the vertical direction of the own vehicle 10.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for detecting lane positions at the left and right front of a vehicle and detecting an approaching vehicle.

[0002]

2. Description of the Related Art As a conventional technique of an image processing apparatus for detecting a vehicle, for example, there is a technique described in Japanese Patent Application Laid-Open No. H11-59272. The technique described in this publication captures and displays an image of the left and right front of the vehicle reflected on a chevron mirror by an image pickup means provided at the tip of the vehicle. Thereby, it is possible to observe the blind spot range in both the left and right directions.

[0003] As a technique similar to the above-mentioned publication, for example, Japanese Patent Application Laid-Open No. 11-338074, Japanese Patent Application Laid-Open
There are those described in JP-A-331834 and JP-A-10-19643.

[0004]

However, according to the above-mentioned prior art, it is possible to observe the blind spot in both the left and right directions of the vehicle, but it is not possible to monitor the forward direction.

Therefore, it is conceivable to use a camera that monitors both the left and right directions of the vehicle and a camera that is arranged at the center of the vehicle and monitors the front direction at the same time.

However, with a camera located in the center of the vehicle, if the vehicle is approaching the preceding vehicle, the preceding vehicle becomes an obstacle and the lane on the road cannot be monitored, making it difficult to detect the lane position. Problem.

An object of the present invention is to realize an image processing apparatus capable of both detecting a lane position and monitoring a blind spot in both left and right directions even when approaching a preceding vehicle.

[0008]

In order to achieve the above object, the present invention is configured as follows. (1) In an image processing apparatus for detecting an approaching vehicle and a lane position, a first imaging unit disposed in the own vehicle and having an area in front of the own vehicle and one side area as an imaging area;
A second image pickup unit is provided in the host vehicle and has a front area and the other side area of the host vehicle as image pickup areas.

(2) Preferably, in the above (1),
When each of the first imaging unit and the second imaging unit captures an image of the traveling lane ahead of the host vehicle in one half of the imaging area, the first imaging unit and the second imaging unit draw an extension of the front end surface of the host vehicle on the other side. Image within half area.

(3) Preferably, in the above (1) and (2), when the own vehicle is at or below a predetermined vehicle speed, it is determined whether or not the own vehicle is located at an intersection, and Is located within the intersection, it is determined whether there is another vehicle approaching.

(4) Preferably, in the above (1) and (2), when the lane position cannot be detected from the video information of one of the first and second imaging units, the other is used. The lane position is detected based on the image information of the imaging unit.

(5) Preferably, in the above (2), each of the first imaging unit and the second imaging unit is 1
One or a plurality of imaging devices, and the imaging device images a wide range in the horizontal direction.

(6) Preferably, in the above (1) and (2), based on the positional relationship between the vanishing point of the lane in the captured image and the horizontal direction of the lane, the lane positional relationship and the lane departure situation are determined. judge.

(7) Preferably, in the above (1) and (2), each of the first imaging section and the second imaging section is integrally formed with the blinker lamp or the like. It has means for blocking light.

According to the present invention constructed as described above, even when approaching the preceding vehicle, the lane is detected by one of the imaging units, the lane position detection is reliably executed, and the monitoring of both the left and right directions of the own vehicle is also performed. It becomes possible.

[0016]

Embodiments of the present invention will be described below in detail with reference to the accompanying drawings. FIG. 1 is a diagram illustrating a system configuration of an image processing apparatus that detects an approaching vehicle position according to an embodiment of the present invention.

In FIG. 1, an image processing apparatus includes an image pickup unit 1 (first image pickup unit) for picking up the right front of the own vehicle, and an image pickup unit 2 (second image pickup unit) for picking up the left front of the host vehicle. A direction instruction operating device 3, a vehicle speed detecting unit 4, a navigation device 5,
Alarm 6, monitor 7, steer controller 8, processing unit 9
And

The processing unit 9 uses the intersection information from the navigation device 5, the own vehicle speed information from the own vehicle speed detecting unit 4, and the right / left turn information from the direction indicating operating device 3 to obtain the left and right imaging units 1, 2.
The lane position detecting process, the interrupting vehicle detecting process, and the intersection approaching vehicle detecting process are performed on the video information from 2.

The lane position detection result output from the processing unit 9 is output to the steering controller 8, and the steering controller 8 controls the vehicle to stably maintain the traveling of the vehicle based on the traveling lane. I do.

The processing section 9 estimates the degree of danger of the own vehicle from the interrupted vehicle detection result, the intersection approaching vehicle detection result, the own vehicle speed information, the right / left turn information, and the like. Alert the person.

Further, the processing section 9 processes the video information in accordance with the estimated degree of danger and displays it on the monitor 7 for the driver. For example, on the display of the monitor 7, when a vehicle approaching the host vehicle is detected, a quadrangle surrounding the detected vehicle is displayed. At this time, the color of the line drawing the quadrangle is changed from green to yellow and red as the degree of risk increases, and the driver is notified of the degree of risk.

Next, with reference to FIG. 2, the mounting positions of the imaging units 1 and 2 on the own vehicle will be described. In FIG. 2, the imaging units 1 and 2 are positioned at both sides (corners) in front of the vehicle 10.
Attach.

Image pickup units 1 and 2 are provided on both front sides of the vehicle 10.
Is attached, the imaging areas of the imaging units 1 and 2 each have a range of 150 degrees in the horizontal direction and a range of 60 degrees in the vertical direction.

Further, the extension of the imaging direction, that is, the extension of the center point of the imaging area in the imaging depth direction is set in a direction inclined by 45 degrees from the traveling direction of the own vehicle 10 with respect to the horizontal direction of the own vehicle 10. .

As a result, the imaging units 1 and 2
The region from the traveling direction of 0 to the region inclined by 30 degrees in the direction of the central axis of the vehicle 10 is the imaging region. Similarly, the imaging unit 1,
In 2, the imaging region is a region that is inclined 30 degrees rearward of the host vehicle 10 from a direction 90 degrees from the traveling direction of the host vehicle 10.

Further, the extension line in the direction of the imaging depth is set three degrees downward in the vertical direction of the vehicle 10.

With the mounting position and posture as described above, the vehicle 1
The image information from the imaging units 1 and 2 attached to the camera 0 is as shown in FIG. 4 when the imaging screen of the imaging unit 1 is a lane marker as shown in FIG. Means that the imaging screen of the imaging unit 1 is inverted left and right.

In FIGS. 3 and 4, L2 is a line shown on the left road surface of the vehicle 10, and R1 and R2 are
It is a line represented on the right road surface with respect to the vehicle 10, and C_X
Is the position in the X direction (horizontal direction) where the lane vanishes on the imaging screen when the host vehicle 10 is traveling straight in the lane,
H indicates the horizon.

In FIG. 3, the horizontal axis represents the distance when the right direction is plus and the left direction is minus with reference to the position where the image pickup unit 1 of the vehicle 10 is mounted, and the vertical axis is the image of the vehicle 10. The distance in the case where the upper direction in FIG. 3 is plus and the lower direction is minus with reference to the position where the part 1 is attached is shown.

In FIG. 4, the horizontal axis and the vertical axis indicate the coordinate positions with respect to the reference coordinates (0, 0) on the image screen.

Here, the internal configuration of the imaging units 1 and 2 will be described with reference to FIG. In FIG. 5, digital image data output from an imaging device 21 composed of a CCD or a CMOS sensor is
Buffer 22-1. This buffer 22
When one line of data is transferred to -1, the buffer 2
The data is transferred from 2-1 to the transmission buffer 22-2, and the data is collectively transferred to the video data storage area in the RAM 25.

The transfer of these data operates in accordance with a synchronization signal output from a T / G (timing generator) 27. The synchronizing signal is a signal indicating one screen segment, one line segment, one pixel segment, or the like.

The image data for one screen is stored in the RAM 2
5 is transferred to the video data storage area in the ROM 5.
CPU 23 performs image processing and image recognition in accordance with the program described in.

The lane marker and the vehicle are extracted by the image processing and image recognition by the CPU 23. The extraction method is omitted here. This extracted information is CAN
26.

The blinking signals of the turn signal lamps 11 and 12 are input from the input / output port 28, and according to the program, the CPU 23 adjusts the amount of light received in the exposure control of the image pickup device 21 when the lamp is turned on.

For example, the CPU 23 sets the shutter speed to 1
By increasing the speed from / 60 to 1/120, the amount of received light is reduced. Conversely, when the turn signal lamps 11 and 12 are turned off, the amount of received light is increased by exposure control of the imaging device 21.

Further, the CPU 23 calculates the curvature of the lane, the lateral distance between the lane and the host vehicle 10, and the traveling direction angle of the host vehicle 10 with respect to the lane from the information of the extracted lane marker.

When the imaging units 1 and 2 are mounted on both front sides of the vehicle 10, the above description has been made such that each imaging unit 1 and 2 uses one imaging device 21 to set the imaging area in the horizontal direction. Is in the range of 150 degrees and 60 in the vertical direction
Had a range of degrees.

However, a single image pickup unit may be provided with two image pickup devices 21-1 and 21-2. Hereinafter, a configuration in which one imaging unit includes two imaging devices 21-1 and 21-2 will be described with reference to FIGS. 6 and 7, one imaging device 21
The imaging direction of −1, that is, the extension line of the center point of the imaging region in the imaging depth direction is, with respect to the horizontal direction of the host vehicle 10,
It is set in the traveling direction of the vehicle 10. The imaging direction of the other imaging device 21-2 is 7
It is set in the direction inclined by 0 degrees.

Here, the imaging devices 21-1 and 21-2
In the image pickup area, images are obtained by overlapping an area of 10 degrees with each other.

As a result, the imaging units 1 and 2
The region from the traveling direction of 0 to the region inclined by 30 degrees in the direction of the central axis of the vehicle 10 is the imaging region. Similarly, the imaging unit 1,
In 2, the imaging region is a region that is inclined 30 degrees rearward of the host vehicle 10 from a direction 90 degrees from the traveling direction of the host vehicle 10.

The extension line in the imaging depth direction is set downward by 3 degrees in the vertical direction of the vehicle 10.

Here, the internal configuration of the imaging units 1 and 2 will be described with reference to FIG. In FIG. 7, imaging devices 21-1 and 21- 21 each comprising a CCD or a CMOS sensor.
The digital image data output from 2 is taken into the buffers 22-1 and 22-3 of the transfer device 22 one pixel at a time. One line of data is stored in buffers 22-1, 22.
When the data is transferred to -3, the data in the buffer 22-1 is transferred to the transmission buffer 22-2, and the data is collectively transferred to the video data storage area in the RAM 25.

Thereafter, the data in the buffer 22-3 is transferred to the transmission buffer 22-2, and these data are put together and transferred to the video data storage area in the RAM 25. The transfer of these data operates according to a synchronization signal output from a T / G (timing generator).
The synchronizing signal is a signal indicating one screen segment, one line segment, one pixel segment, or the like.

Then, the two imaging devices 21-1 and 21-2
When the image data for one screen of 1-2 is transferred to the video data storage area in the RAM 25, the CPU 23 performs image processing and image recognition according to a program stored in the ROM 24.

A lane marker and a vehicle are extracted by image processing and image recognition by the CPU 23. The extraction method is omitted here. This extracted information is CAN26
Output from

Also, a blink signal of the turn signal lamps 11 and 12 is inputted from the input / output port 28, and C is inputted according to the program.
When the lamp is turned on, the PU 23 operates the imaging device 21-.
Adjustments are made so as to reduce the amount of received light by the exposure control of 1 and 21-2.

For example, the CPU 23 sets the shutter speed to 1
By increasing the speed from / 60 to 1/120, the amount of received light is reduced. Conversely, when the lamp is turned off, the amount of received light is increased by exposure control of the imaging devices 21-1 and 21-2.

Further, the CPU 23 calculates the curvature of the lane, the lateral distance between the lane and the own vehicle, and the traveling direction angle of the own vehicle with respect to the lane from the information of the extracted lane marker.

With the mounting position and posture as described above, the vehicle 1
The image information from the image pickup unit 1 attached to the image pickup device 0 indicates that the image pickup device 22-1 is in a state as shown in FIG. 8, that is, the image pickup device 22-1 is between the lines L2 and R2, and When the line R1 is located near and is not in the imaging area, an imaging screen as shown in FIG. 9 is obtained.

The imaging device 22-2 in the state shown in FIG. 10, that is, the imaging device 22-2 is a line L
2 and R2, which is located closer to R2, and when the lines R1 and R2 are in the imaging region but there is no line L1, an imaging screen as shown in FIG. 11 is obtained. .

In FIGS. 8, 9, 10, and 11, L1 and L2 are lines shown on the left road surface with respect to the vehicle 10, and R1 and R2 are lines shown on the right road surface with respect to the vehicle 10. Yes, C_X is the X direction with the vanishing point of the lane on the imaging screen when the vehicle 10 is traveling straight in the lane.
(Horizontal direction), and H indicates the horizon. Here, the internal configuration of the processing unit 9 will be described with reference to FIG. In FIG. 12, the CPU 23 performs processing such as lane position detection and vehicle detection in accordance with a program stored in a ROM 24. Information required for performing these processes is CAN
25 from a variety of devices connected to it. Further, the processing result is output to necessary devices via the CAN 26.

Next, the main processing of the detection processing in the imaging units 1, 2 and the processing unit 9 will be described in detail with reference to FIG. The description of the initialization processing, image capture processing, and the like is omitted here.

In FIG. 13, in step 1, a synthesizing process for averaging video information obtained by the above two exposure controls taken in the left imaging section 2 is performed, and both bright and dark areas have appropriate brightness. And

Next, in step 2, a left edge extraction process is performed on the image synthesized in step 1, and based on the edge extraction process, a left lane position detection is performed in step 3. (The position coordinates of ringworm on the imaging screen are calculated as the processing result, and output to the processing unit via the CAN 26.

Subsequently, in step 4, it is determined whether or not the vehicle speed of the host vehicle 10 (received from the host vehicle speed detection unit) is 10 km / h or more. Then, in step 4, if the vehicle speed of the own vehicle 10 is 10 km / h or more,
Proceeding to step 12, an instruction is issued to the imaging unit 2 via the CAN 26 to perform a process of detecting the left front vehicle.

In step 4, the vehicle speed is 10 km / h
If it is less, the process proceeds to step 11, and the processing unit 9 determines the left intersection.

The determination of the intersection in step 11 is made using the detection result of the lane and the information from the navigation. If it is determined in step 11 that the vehicle is not at an intersection, the process proceeds to step 12, and the subsequent processing is performed.

If it is determined in step 11 that the vehicle is an intersection, the process proceeds to step 13 in which a process of detecting a vehicle approaching the left side of the host vehicle 10 is performed. That is, it detects the presence or absence of a vehicle in a lane parallel to the traveling lane of the host vehicle 10 and further in an intersecting lane. Then, the process proceeds to step 14.

At step 14, the risk of collision with the interrupted vehicle or the oncoming vehicle is determined for the left side of the own vehicle based on the vehicle detection result at step 12 or 13.

Next, the process proceeds to step 21 in which synthesis processing for averaging video information obtained by the two exposure controls taken in the right imaging unit 1 is performed, and both bright and dark areas are adjusted to appropriate brightness. And

Subsequently, the processing proceeds to step 22, where st
A right edge extraction process is performed on the composite video obtained in ep21, and a right lane position detection process is performed in step 23 using the edge extraction result. As a processing result, the position coordinates of the white line on the imaging screen are calculated and output to the processing unit 9 via the CAN 26.

Next, in step 24, the own vehicle speed detector 4
It is determined whether or not the vehicle speed of the vehicle 10 received from the vehicle is 10 km / h or more. Vehicle speed is 10k in step 24
If it is determined that the speed is equal to or more than m / h, in step 32, a process of detecting the right front side vehicle is performed on the imaging unit 1 via the CAN 26. Then, the process proceeds from step 32 to step 34.

If it is determined in step 24 that the vehicle speed is less than 10 km / h, in step 31, the processing unit 9
Is used to determine the right intersection. The determination of the intersection in step 31 is performed using the detection result of the lane or the information from the navigation.

If it is determined in step 31 that the vehicle is not at an intersection, the processing after step 32 is performed.

If it is determined in step 31 that the vehicle is at an intersection, the flow proceeds to step 33 to perform a process for detecting a vehicle approaching on the right side. That is, it detects the presence or absence of a vehicle in a lane parallel to the traveling lane of the host vehicle 10 and further in an intersecting lane. Then, the process proceeds to step 34.

In step 34, step 32 or st
According to the vehicle detection result of ep33, for the right side of the own vehicle,
The risk of collision with the interrupting vehicle or the oncoming vehicle is determined. Then, the process proceeds to step step41.

In step 41, step 3, step
A positional relationship between the host vehicle and the lane is calculated from the left and right lane position detection results processed in 23, and information (a lane position detection result) representing the positional relationship is output.

Next, the positional relationship between the lane and the vehicle 10 will be described.
This will be described with reference to FIGS. 3, 4 and 14 to 17. FIG.
Indicates a right white line 1 m away from the imaging unit 1 on the right side, and indicates a positional relationship of 3 m in lane width. At this time, the video imaged by the imaging unit 1 is as shown in FIG.

FIG. 14 shows the positional relationship when the right white line is located at the same position as the image pickup section 1. At this time, the video imaged by the imaging unit 1 is as shown in FIG.

FIG. 16 shows a positional relationship where the right white line is located 1 m to the left of the image pickup unit 1 and the lane width is 3 m. At this time, the image captured by the imaging unit 1 is as shown in FIG.

Here, the host vehicle 10 is traveling straight in the lane. At this time, the position of the vanishing point of the lane does not change in FIGS. 4, 15, and 17 of the captured video. When the vehicle 10 is traveling in the lane, the white line on the right side is on the right side of the vanishing point as shown in FIG. When the imaging units 1 and 2 are located on the white line, they are on the vertical line of the vanishing point as shown in FIG. When the vehicle 10 is deviating from the lane, the right white line is on the left side of the vanishing point as shown in FIG.

That is, the horizontal position C_X of the vanishing point
Is calculated, and the horizontal position J_X of the intersection of the detected extension line of the white line and the lane position determination line is calculated, and C_X−
The lane position can be determined from the value of J_X.

When the vehicle 10 is traveling diagonally with respect to the lane, the vanishing point moves to the left when traveling diagonally to the right and to the right when traveling diagonally to the left. The vanishing point also moves when the lane is curving. Therefore, the departure time can be estimated from the movement amount.

The imaging units 1 and 2 are composed of two imaging devices 21-
1 and 21-2, the same method can be used as shown in FIGS.

Then, in step 42, step 41
The lane departure degree of the own vehicle is determined from the lane position detection result obtained by the above.

Subsequently, in step 43, step 1
Based on the degree of risk determined in steps 4 and 34, a notification of the presence of an approaching vehicle and an alarm are issued in accordance with the degree of collision risk. Further, an alarm is issued in accordance with the degree of lane departure determined in step 42.

By repeatedly performing the above-described steps 1 to 43, an alarm and a result of lane position detection are output.

Here, the position of the vanishing point, which is important in performing the processing in step 41, is shifted when the mounting direction of the imaging units 1 and 2 is shifted, and the vanishing point position is also shifted, which affects the lane position detection result and the like. Therefore, a method of correcting the vanishing point position will be described with reference to FIG.

In steps 71 to 73 in FIG.
It is determined whether the vehicle 10 is traveling straight. When it is determined that the vehicle is traveling straight, it is determined whether or not a white line is detected in step 74, and if the white line is detected, it is determined in step 75 whether or not a predetermined time has elapsed.

If it is determined in step 75 that the predetermined time has not elapsed, a temporal average position of the vanishing point is calculated in step 76.

If it is determined in step 75 that the predetermined time has elapsed, the flow advances to step 77 to determine whether or not the variance of the calculated average position of the vanishing point is small. This stee
In p77, when the variance of the average position of the vanishing point is small, that is, when it is determined that the vehicle has traveled straight in the straight lane, the process proceeds to step 78, and the vanishing point position is updated to the calculated average position.

As described above, according to the embodiment of the present invention, the imaging area has a range of 150 degrees in the horizontal direction and 60 degrees in the vertical direction at the positions on both sides in front of the vehicle 10. The imaging units 1 and 2 having a range of degrees are attached. The extension line of the center point of the imaging area of the imaging units 1 and 2 in the imaging depth direction is set in a direction inclined by 45 degrees from the traveling direction of the own vehicle 10 with respect to the horizontal direction of the own vehicle 10. Further, the extension lines in the imaging depth direction are set to be 3 degrees downward with respect to the vertical direction of the host vehicle 10 so that the imaging units 1, 2
Set.

Therefore, even when approaching a preceding vehicle, it is possible to realize an image processing apparatus capable of both detecting a lane position and monitoring a vehicle approaching a blind spot in both the left and right directions.

The image pickup units 1 and 2 can be used independently of the vehicle 1
It may be attached to a headlight, a blinker lamp or the like having a waterproof structure. In this case, as a lens of the optical system of the imaging units 1 and 2, a part of the diffusion plate of the turn signal lamp is processed so as to block light from the turn signal lamp and to collect light from the outside. It is also possible.

When the imaging units 1 and 2 are integrally formed with a headlamp or the like, the adjustment of the mounting direction of the imaging units 1 and 2 and the ease of attachment can be improved.

Further, if a headlamp and a wiper for wiping rain and the like attached to the image pickup units 1 and 2 are attached to the front transparent portion, which is integrally formed with the image pickup units 1 and 2,
Still better.

Operation information from the turn signal lamps 11 and 12 or turning lamps is input to the image pickup units 1 and 2 so as to prevent deterioration of exposure conditions due to blinking of the turn signal lamps 11 and 12 and the like. 2 controls the exposure to improve the confirmation of the object to be imaged.

Further, even when the imaging units 1 and 2 receive the light of the headlights of an approaching vehicle (such as an oncoming vehicle), the imaging units 1 and 2 control the exposure so that the optimal exposure condition is obtained.

That is, especially at night, the vehicle 1
The area illuminated by the 0 headlight is bright, and the other areas are dark.

Therefore, the imaging units 1 and 2 alternately perform high-speed exposure control suitable for bright areas and exposure control suitable for dark areas, and output video information to the processing unit 9.

Then, the processing section 9 takes in image information by two exposure controls of exposure control suitable for a bright area and exposure control suitable for a dark area, and performs detection processing of a lane or the like using the image information. .

Further, the blinking of the turn signal lamps 11, 12 or the turning lamp changes the brightness.

Therefore, in synchronism with the flickering cycle, the control amounts of the exposure control suitable for the bright area and the exposure control suitable for the dark area are slightly corrected, and the exposure control is alternately performed at a high speed. Output video information.

The processing section 9 fetches image information obtained by these exposure controls in the image pickup sections 1 and 2 and performs detection processing of a lane or the like using the image information.

[0096]

According to the present invention, two imaging units capable of imaging the front and side of the vehicle are disposed at both front positions of the own vehicle.

Therefore, even when approaching a preceding vehicle, it is possible to realize an image processing apparatus capable of both detecting a lane position and monitoring a vehicle approaching a blind spot in both the left and right directions.

[Brief description of the drawings]

FIG. 1 is a system configuration diagram of an image processing apparatus according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram of a mounting position of an image processing apparatus according to an embodiment of the present invention on a vehicle.

FIG. 3 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 4 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 5 is a configuration diagram of an imaging unit according to an embodiment of the present invention.

FIG. 6 is an explanatory diagram of a mounting position of an image processing apparatus according to an embodiment of the present invention on a vehicle.

FIG. 7 is a configuration diagram of an imaging unit according to an embodiment of the present invention.

FIG. 8 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 9 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 10 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 11 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 12 is an operation flowchart of the image processing apparatus according to the embodiment of the present invention;

FIG. 13 is a configuration diagram of a processing unit according to an embodiment of the present invention.

FIG. 14 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 15 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 16 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 17 is a diagram illustrating a captured image according to an embodiment of the present invention.

FIG. 18 is a flowchart of correcting a vanishing point position according to an embodiment of the present invention.

[Explanation of symbols]

 1, 2 imaging unit 3 direction instruction operation unit 4 own vehicle speed detection unit 5 navigation device 6 alarm 7 monitor 8 steer controller 9 processing unit 10 own vehicle 11, 12 blinker lamp 21 imaging device 21-1, 21-2 imaging Device 22 Transfer device 22-1, 22-2 Buffer 22-3 Buffer 23 CPU 24 ROM 25 RAM 26 CAN 27 T / G 28 Input / output port

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) B60R 21/00 626 B60R 21/00 626G G06T 7/60 150 G06T 7/60 150B 200 200J H04N 7/18 H04N 7/18 J // G08G 1/16 G08G 1/16 CF term (reference) 5B057 AA16 CA12 CA20 CB12 CC03 CH01 DA07 DA15 DA16 DB02 DC03 DC16 5C054 AA05 CA04 CC02 CE01 DA08 EA01 FA00 FF02 HA30 5H180 AA01 CC04 LL01 LL06 LL01 BA04 CA05 DA01 DA03 FA06 FA67 FA69 FA76

Claims (7)

[Claims] 1. An image processing apparatus for detecting an approaching vehicle and a lane position, comprising: a first imaging unit disposed in a host vehicle, and having a front region and one side region of the host vehicle as a shooting region; An image processing apparatus for detecting approaching vehicles and lane positions, comprising: a second imaging unit disposed in the own vehicle and having an imaging region in front of the own vehicle and the other side region. . 2. An image processing apparatus for detecting an approaching vehicle and a lane position according to claim 1, wherein each of the first imaging section and the second imaging section captures a traveling lane in front of the host vehicle. An image processing apparatus for detecting an approaching vehicle and a lane position, wherein an image of an extension of the front end surface of the host vehicle is imaged in the other half area when the image is picked up in one half area. 3. An image processing apparatus for detecting an approaching vehicle and a lane position according to any one of claims 1 and 2, wherein when the own vehicle is at a predetermined vehicle speed or less, Determining whether or not the vehicle is located at an intersection, and determining whether or not there is another approaching vehicle when the own vehicle is located within the intersection. Processing equipment. 4. An image processing apparatus for detecting an approaching vehicle and a lane position according to claim 1, wherein one of the first imaging unit and the second imaging unit. An image processing apparatus for detecting an approaching vehicle and detecting a lane position, wherein the lane position is detected based on the image information of the other imaging unit when the lane position cannot be detected by the image information of the imaging unit. 5. An image processing apparatus for detecting an approaching vehicle and a lane position according to claim 2, wherein each of the first imaging unit and the second imaging unit has one or a plurality of imaging devices. An image processing apparatus for detecting an approaching vehicle and detecting a lane position, wherein the imaging device captures a wide range in the horizontal direction by the imaging device. 6. An image processing apparatus for detecting an approaching vehicle and a lane position according to any one of claims 1 and 2, wherein a position of a vanishing point of the lane in the captured image and a horizontal direction of the lane are determined. An image processing device for detecting an approaching vehicle and a lane position, wherein the image processing device determines a lane position relationship and a lane departure state based on the positional relationship. 7. An image processing apparatus for detecting an approaching vehicle and a lane position according to claim 1 or 2, wherein each of the first imaging unit and the second imaging unit includes: An image processing apparatus for detecting an approaching vehicle and detecting a lane position, comprising means for blocking light from a turn signal lamp or the like when integrally formed with the turn signal lamp or the like.