JPH0594596A - Position detector for vehicle - Google Patents

Abstract

PURPOSE:To surely detect the position of each vehicle by detecting a lighting area on a road surface by headlights of the vehicle and the moving direction of the lighting area from an image obtained by photographing the road from its upper position and finding out the position of the vehicle based upon the detected lighting area and its moving direction. CONSTITUTION:A television(TV) camera 11 for picking up an image from an upper position on a road is arranged on a high position such as a pole 19 of a road lighting lamp and provided with an optical filter 21 so as not to touch an yellow projection part such as a sodium-vapor lamp. An image processing part 13 constitutes a light area detecting means and finds out a lighting area on a road by the headlights of a vehicle, labeling for identification and the centroid position of the lighting area while referring to a road shape data base 15. A vehicle position computing part 17 constitutes a moving direction detecting means and a position computing means and sets up the end point of the lighting area in the opposite direction to the moving direction as the position of the vehicle based upon the movement of the centroid position of the lighting area which is obtained from the image processing part 13.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a vehicle position detecting device for detecting the position of a traveling vehicle, especially at night.

[0002]

2. Description of the Related Art For example, a system has been proposed in which a road illumination lamp is turned on only when a vehicle approaches to save energy, and in this system, detection of the vehicle position is important.

As a vehicle position detecting device for that purpose,
For example, an application of the device disclosed in Japanese Patent Laid-Open No. 62-121599 can be considered. That is, the disclosed device measures the distance to a vehicle ahead by recognizing a vehicle alarm lamp such as a stop lamp by an image pickup means and measuring the distance between the lamps. By installing it on the road side, the vehicle position on the road is detected.

[0004]

However, in the above-described vehicle position detecting device, when the vehicles are traveling in a row due to, for example, traffic congestion, the preceding vehicle is hidden behind the vehicle behind. There is a problem that the warning lamp of the preceding vehicle cannot be reliably caught.

In order to solve this problem, it is easy to install the image pickup means at a high place. However, depending on the installation height of the image pickup means, the image pickup angle, etc., there is a possibility that the alarm lamp mounted vertically at the rear end of the vehicle cannot be caught.

The present invention has been made in view of the above, and an object of the present invention is to provide a vehicle position detection device capable of surely detecting the position of each vehicle.

[0007]

In order to achieve the above object, the present invention is, as shown in FIG. 1, an image pickup means 1 for picking up an image of a road from above, and an illumination on a road surface by a headlight of a vehicle from the picked-up image. Illumination area detection means 3 for detecting an area, movement direction detection means 5 for detecting the movement direction of the detected illumination area, and position calculation means 7 for obtaining the position of the vehicle based on the detected illumination area and its movement direction. Having it is the gist.

[0008]

In the vehicle position detecting device according to the present invention, the illumination area on the road surface by the headlights of the vehicle and the moving direction of the illumination area are detected from the image of the road captured from above, and the detected illumination area and the detected illumination area are detected. The position of the vehicle is determined based on the moving direction.

[0009]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 2 is a diagram showing the structure of a vehicle position detecting device according to an embodiment of the present invention. In FIG. 2, 11 is a television camera which constitutes an image pickup means, 13 is an image processing unit,
Reference numeral 15 is a road shape database unit, and 17 is a vehicle position calculation unit.

As shown in FIG. 3, the television camera 11 picks up an image of the road 18 from above, and is installed at a high position of a pole 19 of a road illumination lamp, for example. An optical filter 21 is provided on the image pickup surface of the television camera 11 so as not to capture a portion of the road projection of yellow road lighting such as a sodium lamp projected onto the road.

The image processing section 13 constitutes an illumination area detecting means, detects the shape of the road 18 in advance based on the image picked up by the television camera 11, and is necessary for the processing in the vehicle position calculating section 17. It seeks information.

The road shape database unit 15 stores data such as the shape of the road 18 of the portion imaged by the television camera 11, the number of lanes, and the speed limit.

The vehicle position calculating section 17 constitutes a moving direction detecting means and a position calculating means, and the image processing section 13
The position of the vehicle is obtained based on the information provided by.

Next, the operation of this embodiment will be described with reference to the processing flowchart shown in FIG.

First, after the image processing unit 13 and the vehicle position calculating unit 17 read out the data required for the calculation from the road shape database unit 15 and perform a predetermined initialization (step 100), the television camera by the image processing unit 13 is executed. Image input (refer to FIG. 5) at a constant time interval (for example, 0.5 seconds) from 11 and processing for ternarizing the input image according to the brightness level thereof are started (steps 110 and 120).
Here, as two kinds of thresholds for ternarization, the headlight of the vehicle is the highest brightness area, the illumination area of the road surface by the headlight of the vehicle is the middle brightness area, and the illumination area is the lowest brightness area. It is set so as to be able to distinguish each road surface which is not, and is a variable value depending on the brightness environment of the road in the evening or morning.

The image processing unit 13 extracts an intermediate luminance portion corresponding to the illumination area of the road surface by the headlights of the vehicle from the image information after the ternarization processing (step 13).
0). It should be noted that the image obtained by this extraction processing is, as shown in FIG.
Not only 5 but also the white line 27 in the vicinity thereof is included.

Next, the image processing unit 13 performs a differentiating process on the image information obtained by this extracting process to extract a portion where the brightness changes drastically, that is, the edges constituting the illumination areas 23 and 25 and the white line 27, and extracts the extracted edges. After confirming that the edge forms a closed loop, the area surrounded by this edge is determined as one block, and labeling is performed to identify each block (step 14).
0). That is, labeling is performed for each of the illumination areas 23 and 25 and the white line 27.

After that, the image processing unit 13 obtains the area of each labeled block, extracts the blocks constituting the illumination area by the headlight based on the size, and calculates the center of gravity of each of the extracted blocks. The position and the block edge (end point) in the front-back direction of the road are obtained (steps 150 to 180). The calculation of the block edge in the front-rear direction of the road is performed by the road shape database unit 1.
This can be easily done based on the data on the road shape read from No. 5. The result of the processing here is shown in an image as shown in FIG. In FIG. 7, 31 is a road shape in a database, 33 and 35 are centroids of blocks, and 37, 39, 41 and 43 are end points of each block. Then, this image information is input to the vehicle position calculation unit 17, and the position of the vehicle is obtained in the processing of step 190 and subsequent steps. In step 170, if none of the areas of the blocks have reached the predetermined value, it is considered that none of the blocks is the illumination area, and step 11
Return to 0.

In step 190, the vehicle position calculating section 17 temporarily stores the image information from the image processing section 13, and then determines whether or not the image information is input first (step 200). If it is the first time, the process returns to step 110 and waits for the input of the next image information. If not the first
The vehicle position calculation unit 17 determines the moving direction of the gravity center position by comparing the gravity center positions of the image information input this time and the image information input last time, and obtains the end point in the direction opposite to the moving direction as the position of the vehicle (step). 210-23
0). That is, in FIG. 7, if the moving directions of the centers of gravity 33 and 35 are upward in the drawing, the end points 39 and 43 are obtained as the vehicle position.

Therefore, according to the present embodiment, the illumination area projected on the road surface from a high place is recognized, and the vehicle position is obtained based on this illumination area and its moving direction. There is no inconvenience such as the method of capturing the lamp, and the vehicle position can always be recognized.

In this embodiment, the moving direction of the vehicle is determined as the moving direction of the center of gravity of the block, but it may be determined based on the edge (end point) of the block.

[0023]

As described above, according to the present invention, the illumination area on the road surface by the headlights of the vehicle and the moving direction of the illumination area are detected from the image of the road captured from above, and the detected illumination area and the detected illumination area are detected. Since the position of the vehicle is obtained based on the moving direction, it is possible to reliably detect the position of each vehicle.

[Brief description of drawings]

FIG. 1 is a diagram corresponding to a claim of the present invention.

FIG. 2 is a diagram showing a configuration of an exemplary embodiment of the present invention.

FIG. 3 is a diagram for explaining the configuration of the embodiment.

FIG. 4 is a diagram showing a processing flowchart of the embodiment.

FIG. 5 is a diagram for explaining a process of the embodiment.

FIG. 6 is a diagram for explaining a process of the embodiment.

FIG. 7 is a diagram for explaining a process of the embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Imaging means 3 Illumination area detection means 5 Moving direction detection means 7 Position calculation means 11 TV camera 13 Image processing section 15 Road shape database section 17 Vehicle position calculation section 18 Road 19 Pole 21 Optical filter 23, 25 Illumination area 27 White line

Claims (1)

[Claims] 1. An image pickup means for picking up an image of a road from above, an illumination area detection means for detecting an illumination area on a road surface by a headlight of a vehicle from the imaged image, and a moving direction for detecting a moving direction of the detected illumination area. A vehicle position detecting device comprising: a detecting unit; and a position calculating unit that obtains the position of the vehicle based on the detected illumination area and the moving direction thereof.