JPH03282708A - Travel controller for mobile vehicle - Google Patents

Abstract

PURPOSE:To perform velocity control in accordance with the state of its own vehicle and to travel the vehicle at constant speed naturally and smoothly by correcting the velocity control by a constant travel means based on the state before the vehicle recognized by a state recognizing means. CONSTITUTION:This controller is equipped with an image input means 1 for the recognition of an outside field, the constant travel means to travel the vehicle at constant speed, and a travel path area extracting means to extract a travel path area with an input image. Also, it is equipped with the state recognizing means which recognizes the state before the vehicle based on the travel path area extracted by the travel path area extracting means, and a control correction means which corrects control by the constant travel means based on the state before the vehicle recognized by the state recognizing means. Thereby, it is possible to perform automatic velocity control in accordance with the state before the vehicle recognized by image processing.

Description

DETAILED DESCRIPTION OF THE INVENTION (Field of Industrial Application) The present invention relates to a travel control device for mobile vehicles that controls the speed of its own troops according to road conditions recognized through image processing.

(Prior art) Conventionally, when maintaining a constant speed of a vehicle, the vehicle obtains information about its own acceleration and deceleration from a speed sensor, and uses that information to maintain the set speed. It controlled the accelerator opening.

(Problem to be solved by the invention) However, in the above conventional example, a speed sensor detects the acceleration/deceleration of the own vehicle, and when the speed of the own vehicle decreases, the accelerator is opened, and when the speed of the own vehicle increases, the accelerator is closed. This control has the following drawbacks.

(1) The accelerator may be suddenly opened and closed to maintain speed, making accelerator control unnatural. (In turbo cars, a phenomenon occurs where the turbo suddenly becomes effective.) (2) The accelerator is opened and closed only when the vehicle speed decreases when going uphill or increases when going downhill, so speed control is smooth. is not carried out.

(Means for Solving the Problems) The present invention has been made for the purpose of solving the above-mentioned problems, and includes the following configuration as one means for solving the above-mentioned problems.

That is, an image input means for recognizing the external world, a constant speed traveling means for driving the vehicle at a constant speed, a traveling road region extracting means for extracting a traveling road region based on the input image, and a driving road region extracting means for extracting a traveling road region based on the input image. a situation recognition means for recognizing the situation in front of the vehicle based on the traveling road area extracted by the means; and a control correction means for correcting the control by the constant speed traveling means based on the situation in front of the vehicle recognized by the situation recognition means. Equipped with

(Function) With the above configuration, speed control can be performed according to the situation in front of the vehicle recognized by image processing.

(Embodiment) Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a block diagram of a travel control device for a mobile vehicle, which is an embodiment of the present invention.

In FIG. 1, a travel control device for a mobile vehicle (hereinafter referred to as a travel control device) includes an image input unit 1 consisting of a video camera, etc.
An image of the front of the own vehicle is inputted from the input image, and the input image is binarized by the image binary conversion unit 2. Then, in the edge extraction section 3, 2
Edges are extracted from the converted image using the method described later. The image after edge extraction is sent to the forward vehicle recognition unit 4,
The forward vehicle recognition unit 4 recognizes the presence or absence of a vehicle in front of the vehicle based on the image. In addition, the sensor unit 5 constantly monitors the speed and direction of movement of the own vehicle to detect the speed and amount of movement of the own vehicle,
The detection result is sent to the forward vehicle recognition section 4.

The own vehicle situation recognition section 6 inputs the binarized image of the front of the own vehicle from the image binarization section 2, and recognizes the road situation in front of the own vehicle using a method described later.

The main calculation unit 7 inputs the road situation in front of the own vehicle from the own force situation recognition unit 6, receives information from the forward vehicle recognition unit 4 as to whether or not there is a vehicle in front of the own vehicle, and responds to the situation. The degree of acceleration and deceleration of the own vehicle is calculated, and the calculation result is sent to the accelerator control unit 8.
send to Then, the accelerator control unit 8 receives the calculation result from the main calculation unit 7 and adjusts the accelerator opening.
The speed of the own vehicle is accelerated, decelerated, or maintained at the current speed.

Hereinafter, the vehicle speed control method in the travel control device of this embodiment will be described in detail.

First, with reference to FIGS. 2(A) and 2(B), a method for extracting white lines on a road from an image taken in front of the vehicle will be described.

FIG. 2(A) is an image taken by the image input unit 1,
FIG. 2(B) is an image after the image in FIG. 2(A) has been binarized by the image binarizing section 2. The threshold value for binarizing the image in the image binarization unit 2 is based on the average value of the binarized area A, where the area A at the bottom center of the screen in FIG. 2 (A) is taken as a road area. decide. Therefore, with this threshold value, Figure 2 (
When the image A) is binarized, the white line on the road can be extracted as shown in FIG. 2(B), and the area S indicated by diagonal lines can be determined.

Next, in order to determine whether or not there is a vehicle in front of the host vehicle, the edge extraction unit 3 uses the mask shown in FIG. Perform directional edge extraction. That is, as shown in FIG. 4(A),
If there are shadows 20a and 21a caused by objects 20 and 21 in region S, when edge extraction is performed from the bottom of the screen upwards, the upper part is darker than the lower part, that is, the part that changes from bright to dark is extracted as an edge. be done. The actual size of the object can be determined by measuring the width of the extracted portion, that is, the length of the edges, so those that exceed a certain value are narrowed down and saved as moving object candidate points, while other Remove things as noise. As a result of narrowing down the moving object candidate points, an image shown in FIG. 4(B) is obtained.

Furthermore, after a predetermined period of time (denoted as Δt) has elapsed after taking the image shown in FIG. ), extract the edges in the horizontal direction of the image using the same method as described above,
Edges 22b and 23b shown in FIG. 4(D) are taken as moving object candidate points on the screen. Note that, for convenience, white lines on the road are written on the image after edge extraction. Also,
It is assumed that two consecutive images of the own troops moving at a certain speed are taken with a time interval Δt long enough to allow the movement of the photographed stationary object on the screen to be recognized.

Recognition of a vehicle in front of the vehicle is performed by comparing images taken at time intervals of Δt and determining whether a common moving object candidate point exists in both images. That is, the forward vehicle recognition unit 4 determines moving object candidate points 20b, 21b, 22b, and 23b from the images shown in FIG. 4CB) and FIG. The positions of edges 20b and 23b have moved between the two screens, and edge 2
It can be seen that the positions of 1b and 22b on the screen do not change. Therefore, a calculation is performed to determine whether the movement amount of the own army detected by the sensor unit 5 matches the movement amount of the edges 20b and 23b on the screen, and if they match, the edges 20b and 23b
is determined to be an edge extracted from the region S, that is, the shadow of the same stationary object on the road. Further, the forward vehicle recognition unit 4 determines that the edges 21b and 22b, which have been determined not to be moving on the screen, are moving objects in front of the own vehicle, that is, edges extracted from the forward vehicle, and at the same time can confirm that they are the forward vehicle. The distance between the moving object candidate point and the lower edge of the screen (D in Fig. 4 (B))
From this, calculate the distance between your vehicle and the vehicle in front.

Next, we will discuss how to recognize the situation of your own vehicle.

The own vehicle situation recognition unit 6 performs the image processing described below based on the image binarized by the image binarization unit 2 to determine the road situation in front of the own vehicle.

FIG. 5(A) shows an image taken by the image binarization unit 2 of a road where the vehicle is positioned on a flat surface and the road in front of the vehicle is upward.
This figure shows how tangent lines (indicated by broken lines) are drawn to each line indicating the road edge after the white line (solid line part) on the road is extracted.

Then, when finding the intersection C1 of the tangents, we find the intersection C1
1 is located below the point V (point at infinity) where the lines indicating the road edges intersect. Similarly, when finding the intersection points for images of a flat road in front of the vehicle and images of a road going down, the results are shown in Figures 5 (B) and 5 (C).
). That is, on a road where the road ahead of the vehicle is also flat, the intersection C2 will be at the same location as the intersection V2 (point at infinity), and on a road where the road ahead of the vehicle is downhill, the intersection C3 will be at the same location as the intersection V3 (point at infinity). located above.

In other words, by finding the intersection of the line indicating the road edge, which is the point at infinity, and the intersection of the tangent to the line indicating the road edge, and comparing the vertical positional relationship of these intersection points, It is possible to recognize situations in which the road ``soon goes up'', remains flat'', or ``eventually goes down''.

The main calculation unit 7 inputs the presence or absence of a vehicle in front of the own vehicle and the distance to the own vehicle from the forward vehicle recognition unit 4, and also inputs the road situation in front of the own vehicle from the own force situation recognition unit 6, and calculates the Based on the information, control information for the accelerator opening shown in FIG. 6 is calculated. Then, the accelerator control section 8 receives these control information from the main calculation section 7, adjusts the accelerator opening degree, and controls the speed of the own vehicle.

As shown in Figure 6, the accelerator opening during constant speed driving is: (1) Maintain the current level, (2) Slightly close, (3) Medium close, and (4) Large (close). (5) Slightly open (6) Moderately closed By accelerating your own troops as open (°), you can prevent deceleration of 1 on the uphill road, and if there is a vehicle ahead near your vehicle on the same uphill road, accelerate the vehicle taking into account that the vehicle ahead will not accelerate either. Control is performed to maintain the distance between your vehicle and the vehicle in front by leaving the opening as it is.

On the other hand, if there is a vehicle in front of you far away and your vehicle is recognized as approaching a downhill road, the accelerator opening degree will be set to "moderately closed" to slow down your vehicle and control your vehicle. The vehicle can run at a constant speed without the driver stepping on the brake on the descent.

As explained above, according to this embodiment, image recognition is performed in front of the vehicle to recognize the presence or absence of a vehicle ahead and the road condition.
Since the speed of the own vehicle can be controlled based on the results, there is no need to operate the accelerator for deceleration on the uphill while driving at a constant speed, or the brake operation for acceleration on the downhill. This has the effect of being able to run at a constant speed.

Furthermore, since the accelerator opening does not change suddenly, it is possible to provide a vehicle with good riding comfort.

In the above embodiment, edge extraction is performed based on the brightness of the binarized image to search for candidate points of a moving object, but edge extraction may be performed using a color image.

In other words, since the shadow directly below the vehicle is dark, its color component does not include the color component of the road itself, and since the shadow contains RG and B in the same size, the color of the shadow in the image By analyzing the components, it is possible to easily distinguish between the shadow directly below the vehicle and the shadow with color components similar to those of the narrow road, and more accurate candidate point extraction of moving objects becomes possible.

Furthermore, when the own vehicle is moving at a constant speed, if the edge 22b in FIG. 4(D) is above 21b in FIG. 4(B) on the screen, the forward moving object 21 is higher than the own vehicle. This means that the forward moving object 21 is moving at a fast speed, and in the opposite case, the forward moving object 21 is moving at a slower speed than the own vehicle. And, Fig. 4 (B
) If the edge 21b in Figure 4 (D) is at the same position on the screen, it can be determined that the forward moving object 21 is moving at the same speed as the own army, so calculate the speed of the vehicle in front. This allows the speed of the own vehicle to be controlled more precisely.

(Effects of the Invention) As described above, according to the present invention, by performing speed control according to the situation of the steering wheel, there is an effect that natural and smooth constant speed running can be achieved.

[Brief explanation of the drawing]

FIG. 1 is a block diagram of a travel control device for a moving vehicle, which is an embodiment of the present invention. FIG. 2(A) is a diagram showing an image captured by an image input unit. FIG. A diagram showing an image binarized by the image binarization unit. Figure 3 is a diagram showing a mask for extracting edges in the horizontal direction of the image. Figure 4 (A) is an image taken in front of the vehicle. FIG. 4(B) is a diagram showing the image after narrowing down the moving object candidate points in the image of FIG. 4(A), and FIG. 4(C) is a diagram showing the image of FIG.
Figure 4 (CD) is a moving object candidate for the image in Figure 4 (C,). 5 Complement points Figure 5 shows the image after narrowing down the images.
A) is a diagram showing the positional relationship between the point at infinity on an uphill road and the intersection point of the tangent line. Figure 5 (B) is a diagram showing the positional relationship between the point at infinity and the intersection point of the tangent line on a flat road. Figure (C) is a diagram showing the positional relationship between the infinity point of the downhill road and the intersection of the tangent line, and Figure 6 is a diagram showing the relationship between the own vehicle situation and the accelerator opening. In the figure, 1... Image human power section, 2... Image binarization section, 3
... Edge extraction section, 4... Front vehicle recognition section, 5...
-Sensor unit, 6... Own vehicle situation recognition unit, 7... Main calculation unit, 8... Accelerator control unit, 20... Stationary object, 2
1...It is an object moving forward. Figure 4 (A) Figure 4 (C) Figure 4 (B) Figure 4 (D)

Claims (1)

[Scope of Claims] A traveling control device for a moving vehicle equipped with an image input means for recognizing the outside world, comprising a constant speed traveling means for making the vehicle travel at a constant speed, and a traveling road area based on the input image. a driving road area extracting means for extracting a driving road area; a situation recognition means for recognizing a situation in front of the vehicle based on the driving road area extracted by the driving path area extracting means; A travel control device for a mobile vehicle, comprising: control correction means for correcting control by the constant speed travel means based on the constant speed travel means.