JPH07192117A - Obstacle detector for vehicle - Google Patents

Abstract

PURPOSE:To reduce and simplify the processing amount of an obstacle detection processing and to realize a high speed processing and the reduction of the cost of an obstruct detector by judging a running lane and executing a processing for only an area which is necessary for an alarm, that is, the measuring area by a distance measuring means. CONSTITUTION:A window processing part 105 segments the only measured range of an optical radar 101 as a window (the detection window of a road surface area) from the image inputted from an image input part 102. In a road surface detection part 106, an object other than the road surface such as a white line part, a preceding vehicle or an obstacle, etc., within the window. In a judgement part 108, the measured result of the optical radar 101 and the detected straight line result are compared. As a result, if it is judged that the preceding vehicle detected by the optical radar 10 is positioned ahead of the line that a car in use runs, the result is outputted to an alarm/control part 104. Further, in the alarm/control part 104, an alarm output and a deceleration control, etc., are executed.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a straight line type of a boundary of a road surface area and a measured distance to an obstacle in order to execute automatic vehicle control, preventive safe driving, or front vehicle following type automatic speed control. The present invention relates to a vehicle obstacle detection device that determines a traveling lane based on a vehicle lane.

[0002]

2. Description of the Related Art As a conventional vehicle obstacle detecting device, for example, a "traveling road detecting device" disclosed in Japanese Patent Laid-Open No. 4-36878 and Japanese Patent Laid-Open No. 62-273477.
A "vehicle surroundings monitoring device" disclosed in Japanese Patent Publication is known.

The "traveling road detecting device" disclosed in Japanese Patent Laid-Open No. 4-36878 detects an edge point inside the traveling road after detecting the traveling road, and the edge cluster is continuously present for a certain time. It is detected as an obstacle when it is determined that it is present.

The "vehicle surroundings monitoring device" disclosed in Japanese Patent Laid-Open No. 62-273477 is located in front of the vehicle by rotating an ultrasonic sensor and an infrared imaging camera according to the running condition of the vehicle. The existence of life forms such as pedestrians is determined and the driver is notified.

Further, in addition to the above, like a laser radar, the light is emitted and the reflected light is received, and the distance to the preceding vehicle or obstacle is detected based on the round-trip time difference from light emission to light reception. Many devices are known.

[0006]

However, the conventional device as described above has the following problems. That is, in the "traveling road detecting device" disclosed in Japanese Patent Application Laid-Open No. 4-36878, when image processing is executed, detection simply depending on the presence or absence of an edge is executed. As described above, there are problems that characters and patterns drawn on the road surface are erroneously detected as obstacles, and there are many errors in distance measurement.

Further, the "vehicle surroundings monitoring device" disclosed in Japanese Patent Laid-Open No. 62-273477 has a problem that high speed processing cannot be performed because the entire captured image is processed as a detection target. . Further, in the case of using the above laser radar, in a curve on a traveling road, a vehicle in another lane or a reflector installed in a roadside zone,
There was a problem that it would be detected as a front obstacle.

The present invention has been made in view of the above, and specifies a road surface area necessary for warning and control, executes processing such as obstacle presence / absence determination only in the area, and detects obstacles. The objective is to realize high-speed processing and cost reduction of the device by reducing and simplifying the processing amount.

[0009]

In order to achieve the above object, the present invention provides a distance measuring means for measuring a distance to an obstacle in front of the host vehicle, and image information obtained by capturing a state in front of the host vehicle. Image input means for inputting a road surface area, road surface area extracting means for extracting a road surface area from a captured image from the captured image input means, and road surface for detecting a linear expression of a boundary of the road surface area extracted by the road surface area extracting means. Detection means,
First judging means for judging a traveling lane based on a straight line type of the boundary detected by the road surface detecting means and a distance to the obstacle measured by the distance measuring means; and the obstacle is the traveling lane. Second to determine whether or not exists
And the determination means of.

[0010]

The obstacle detecting device for a vehicle according to the present invention inputs imaged image information through the imaged image inputting means, extracts a road surface area from the image information, and further uses the road surface area extracting means to extract the road surface area. The straight line formula of the boundary is detected, the traveling lane is judged based on the straight line formula of the boundary and the distance measured by the distance measuring means, and only the area necessary for the alarm, that is, the measurement area by the distance measuring means is processed. Run.

[0011]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a vehicle obstacle detecting device according to the present invention will be described below with reference to the accompanying drawings. FIG. 1 is a block diagram showing a schematic configuration of a vehicle obstacle detection device according to this embodiment. It is roughly installed in the front of the vehicle, and an optical radar 101 using a laser radar and also installed in the front of the vehicle. , An image input unit 102 for inputting a captured image in front of the vehicle, an image signal from the image input unit 102, and an integrated process with a signal from the optical radar 101,
The image processing unit 103 executes the presence / absence judgment of a preceding vehicle, and the alarm / control unit 104 executes automatic control such as alarm output and brake control.

Further, the image processing section 103 is a window processing section 1 for inputting image data from the image input section 102.
05 and a road surface detection unit 106, and a determination unit 108 that outputs control information to the alarm / control unit 104 based on the output from the optical radar 101 and the output from the road surface detection unit 106. It consists of and.

Next, the operation will be described. Optical radar 1
The distance information between the front obstacle and the host vehicle detected by 01 is input to the determination unit 108 in the image processing unit 103. At the same time, the image information obtained by imaging the front of the vehicle is
The image is input from the image input unit 102 to the window processing unit 105 in the image processing unit 103. In the window processing unit 105, a road surface area (window) is applied to the input image.
Is cut out and output to the road surface detection unit 106. After that, the road surface detection unit 106 executes the boundary linear detection process described later, and outputs the result to the determination unit 108. The determination unit 108 determines the traveling lane based on the distance information to the obstacle and the linear expression of the boundary, and outputs the determination result as a control signal to the alarm / control unit 104. The alarm / control unit 104 executes alarm output, deceleration control, etc. based on the determination result from the determination unit 104.

Next, the operations of the window processing unit 105, the road surface detecting unit 106, the judging unit 108, and the alarm / control unit 104 in this embodiment will be described in detail. First, the window processing unit 105 cuts out only the measurement range of the optical radar 101 as a window (road surface region detection window) from the image input from the image input unit 102. Figure 2
FIG. 6 is an explanatory diagram showing a window cutout state by the window processing unit 103, in which a hatched portion indicates a window
01. In this case, it is assumed that both the optical radar 101 and the captured image input means (image input unit 102) are fixed at a predetermined position in front of the vehicle. And the optical radar 1
When the measurement range (measurement area) of 01 is known, the measurement range of the optical radar 101 in the captured image, that is, the window 201 can be fixedly determined. Therefore, the following processing is performed in the window 20
It is executed within the range of 1.

In the road surface detection unit 106, the window 201
Detects white lines, preceding vehicles, obstacles, etc. other than the road surface. FIG. 3 is an explanatory diagram showing an example of detection of a road surface area by the road surface detection unit 106. First, after performing edge detection in the window 201, straight line detection is executed. For example, in FIG. 3A, since the white line is longer than the straight line of the contour of the preceding vehicle, the white line is output as the detection straight line. On the other hand, in FIG. 3B, since the white line is hidden by the preceding vehicle, the horizontal edge of the preceding vehicle is output as the detection straight line.

In the detection line, the x-axis is the horizontal axis (direction orthogonal to the traveling direction), and the y-axis is the vertical axis (same direction as the traveling direction).
If x = a · y + b, then a and b are output. The y-axis passes through the center of the window 201.

Next, the operation of the judgment unit 108 will be described. Assuming that the measurement distance by the optical radar 101 is D, the point on the road surface in front of D can be represented on the image by the equation y _D = F · H / D. It should be noted that F is the focal length of the lens and H is the height of the camera, and both values are known.

When compared with the result of the detected straight line from the road surface detection unit 106, if the detected straight line is the lower portion of the preceding vehicle, y _D and b are substantially equal values. Also,
Since the horizontal edge of the preceding vehicle is likely to be detected,
As shown in FIG. 3B, a becomes almost zero. On the other hand, as shown in FIG. 3 (a), if the preceding vehicle is traveling in the lane to the left of the own lane in the left curve, a is 0
It becomes a large value as compared with, and b becomes a considerably small value with respect to y _D.

From the above, the measurement result of the optical radar 101 and the above detection straight line result are compared. As a result, when a is almost 0, the preceding vehicle detected by the optical radar 101 is in the own lane. It is determined that the vehicle is located in front, and the result is output to the alarm / control unit 104. In addition, the optical radar 1
When the obstacle is not detected by 01, it is determined that the preceding vehicle does not exist. On the other hand, the road surface detection unit 106 does not detect the straight line, and the optical radar 10
If the preceding vehicle is detected by 1, it is determined that there is a vehicle having a density (same system color) similar to that of the road surface, or that the road surface is not detected due to backlight or the like, and there is a preceding vehicle. to decide.

The alarm / control unit 104 controls to issue an alarm or decelerate when a preceding vehicle is present in front of the own lane and is approaching, for example. It is also possible to determine whether the road is a right curve or a left curve from the value of a. further,
It is also possible to know the size of the curve of the road from the size of the absolute value of a (when a is small, a sharp curve), for example,
When the vehicle speed is high and the curve is tight, it is possible to issue an alarm or control the vehicle to decelerate.

Next, another embodiment of the road surface detection unit 106 will be described. In this embodiment, since color is used instead of edge detection and straight line detection, a color camera is used as the captured image input means.

FIG. 4 is a block diagram showing the flow of the detection processing of the road surface detection unit 106. In the figure, first, the color of the lower end portion of the window 201 is extracted (S401).
Since the lower end of the window 201 is very near, it is unlikely that the preceding vehicle is imaged. Therefore, the color of the road surface can be detected from the lower end portion of the window 201.

Next, the degree of similarity with the color extracted in the window 201 is calculated, and a similar color (for example, the same color) is calculated.
The pixel of is detected (S402). After that, labeling processing (area division) is executed (S403), the area is obtained for each area, and only the area having the maximum area is extracted (S40).
4). Then, with respect to the region having the maximum area, projection is performed in parallel with the x-axis, and the frequency for y is obtained (S40).
5). Finally, the peak value is detected from the frequency distribution (S4
06), the y coordinate giving the peak is output as b.
Alternatively, in the above, not the peak value but the uppermost y coordinate exceeding a certain threshold is output as b (S40
7) It is also possible to detect a straight line (S408). Figure 5
And FIG. 6 shows each detection example.

That is, in FIG. 5 and FIG.
The same color is extracted from the image information shown in (a) and FIG. 6 (a) to obtain the images shown in FIGS. 5 (b) and 6 (b). Then, labeling and extraction of the maximum area region are performed on the images shown in FIGS. 5B and 6B, and the images shown in FIGS.
The image shown in (c) is obtained. Furthermore, FIG. 5 (c) and FIG.
The images shown in FIGS. 5D and 6D are obtained by extracting the maximum y coordinate and detecting the straight line with respect to the image shown in FIG. On the other hand, the images shown in FIGS. 5 (e) and 6 (e) are obtained by y-axis projection and peak detection on the images shown in FIGS. 5 (c) and 6 (c).

Further, the judging unit 108 judges that there is a preceding vehicle in the lane when b and y _D are substantially equal to each other or when b> y _D , while when b <y _D , the adjacent vehicle is judged. It is determined that there is a preceding vehicle in the lane.

Further, in this embodiment, the portion of the same color as the road surface is detected, and the road surface area is interrupted by the white line or the preceding vehicle. Further, since the road surface area having the maximum area is considered to be an area including the area immediately in front of the vehicle, this is a method for checking how far the area is continuous. By using this method, it is possible to detect a road surface area that is less affected by a step or a shadow on the road surface, which has the advantage of improving the accuracy of information.

In this way, as shown in FIGS. 5 and 6, the road surface area is extracted from the imaged screen, and the linear expression of the road surface area and the boundary is detected, and the linear expression of the boundary and the optical radar 101 are detected. The traveling lane is determined based on the distance detected by. Therefore, the area required for alarm, namely,
The processing only needs to be executed for the measurement area of the optical radar 101, and since the processing amount is small, high-speed processing is realized.

The maximum y-coordinate with respect to the x-axis is obtained from the region having the maximum area in this embodiment, and then,
By performing the straight line detection, similarly to the above-described embodiment, the degree of the curve or the left or right curve can be well known.

As described above, the distance measurement result by the optical radar 101 and the captured image processing result by the image input unit 102 are integrated, and only the region corresponding to the measurement range (window 201) of the optical radar 101 in the image is obtained. By executing the extraction processing of the non-road surface area or road surface area such as white lines and obstacles, the preceding vehicle in front of the own lane can be detected. In addition, the simple configuration and high speed processing can be performed. This can be realized and the cost of the device can be reduced.

[0030]

As described above, according to the vehicle obstacle detection device of the present invention, the imaged screen is input from the imaged image input means, and the road surface area is extracted from the screen.
Further, the road surface area extracting means detects a straight line expression of the boundary of the road surface area, the traveling lane is judged based on the straight line expression of the boundary and the distance measured by the distance measuring means, and an area necessary for warning, that is, Since the processing is executed only for the measurement area of the distance measuring means, the processing amount of the obstacle detection processing can be reduced and simplified, and high-speed processing and cost reduction of the device can be realized.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration of a vehicle obstacle detection device according to the present invention.

FIG. 2 is an explanatory diagram showing a window cutout state by a window processing unit shown in FIG.

FIG. 3 is an explanatory diagram showing an example of detection of a road surface area by the road surface detection unit shown in FIG.

4 is a block diagram showing a flow of road surface area detection processing by a road surface detection unit shown in FIG. 1. FIG.

FIG. 5 is an explanatory diagram showing an example of a straight line type detection process of a road surface area and a boundary according to the present invention.

FIG. 6 is an explanatory diagram showing an example of a straight line type detection process of a road surface area and a boundary according to the present invention.

[Explanation of symbols]

 101 Optical Radar 102 Image Input Unit 103 Image Processing Unit 104 Alarm / Control Unit 105 Window Processing Unit 106 Road Surface Detection Unit 107 In-Window Road Surface Detection Unit 108 Judgment Unit

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Internal reference number FI technical display location G06F 15/62 415

Claims (1)

[Claims] 1. A distance measuring means for measuring a distance to an obstacle in front of the own vehicle, a picked-up image input means for inputting image information of a state in front of the own vehicle, and an image pick-up from the picked-up image input means. A road surface area extracting means for extracting a road surface area from an image; a road surface detecting means for detecting a boundary linear expression of the road surface area extracted by the road surface area extracting means; and a boundary linear expression for the boundary detected by the road surface detecting means. First determining means for determining a traveling lane based on the distance to the obstacle measured by the distance measuring means, and second determining means for determining whether or not the obstacle exists in the traveling lane. An obstacle detection device for a vehicle, comprising: