JPH0383473A - Car detector - Google Patents

Abstract

PURPOSE:To detect only a car without fail by digitizing a picture signal which is obtained by executing image pickup to the inside of a monitoring area, and executing space differentiation, binarization and labeling and executing matching to each extracted area by using a circular template. CONSTITUTION:The picture signal obtained by an image pickup means 1 is digitized by an A/D converting means 2 and the digital signal of one bit or plural bits is obtained for each picture element. Then, the isotropic space differentiation, namely, differentiation processing not depending on a direction is executed by a space differentiating means 4 and a differentiating absolute value is calculated. In a labeling means 6, labeling is executed to the plural divided areas of the binary picture, which is obtained by a binarizing means 5, and it is detected by a circle detecting means 7 whether, each labeled area is circular or not. When the circular area is existent, a comparison deciding means 9 judges that the car is existent. When the central coordinates of the circle are coincident with the radius, it is judged that the car is stopped, and a judged result is outputted.

Description

[Detailed Description of the Invention] (Industrial Application Field) The present invention applies image processing technology to determine whether a vehicle exists in a monitoring area or whether a vehicle is stopped. The present invention relates to a vehicle detection device that automatically detects a vehicle.

[Conventional technology]

Conventionally, a moving object detection device (motion detector) has been proposed as a device that is relatively similar to a vehicle detection device that applies this type of image processing. This calculates the difference between temporally consecutive images, counts the number of pixels that have changed, and issues an alarm when the change is large.

[Problem to be solved by the invention]

However, the above-mentioned detection device has a problem in that even if a detection object other than a vehicle, such as a human, appears, a change in the image is detected and an alarm is issued. Furthermore, when the vehicle stops, there is no change in the image, resulting in a problem of false alarms.

The present invention has been made in view of the above points,
The purpose is to provide a vehicle detection device that can reliably detect only vehicles. Another object of the present invention is to provide a vehicle detection device that can detect that the vehicle is stopped even when the vehicle is stopped.

[Means to solve the problem]

The vehicle detection device of the present invention includes an imaging means for photographing a monitoring area to obtain an image signal, an A/D conversion means for digitizing the image signal obtained by the imaging means, and a storage for storing the digitized image data. a storage means for determining the absolute differential value of the output from the storage means; a spatial differentiating means for calculating the differential absolute value with respect to the output from the storage means; and 2.
a digitizing means, a labeling means for labeling each divided region of the differential image data binarized by the binarizing means, and a circle detecting means for detecting a circular region for each labeled region. and a comparison determination means for determining the presence of a vehicle based on the circle detection result outputted from the circle detection means, further comprising a comparison determination means for determining the presence of a vehicle based on the circle detection result outputted from the circle detection means, and further comprising a comparison determination means for determining the presence of a vehicle in the circle detection means. It has a circle detection result storage means which adds a calculation function and stores circle detection results such as the center coordinates and radius of the circle, and the circle detection result storage means outputs from the circle detection result storage means for the previous image and for the current image. The present invention is characterized in that it is determined whether the vehicle has stopped by comparing the circle detection results.

[Effect]

In the vehicle detection device of the present invention, the image signal obtained by imaging the monitoring area is digitized, spatially differentiated, binarized, and labeled, and as a result, for each extracted area, By performing matching using a circular template, only the shape of the wheel portion, which is a characteristic of the vehicle, that is, the circular region, is detected, thereby reliably detecting only the vehicle.

Furthermore, the circle detection results such as the center coordinates and radius of the detected circular area are memorized, the circle detection results for the previous image and the current image are compared, and if the - degree is high, the vehicle is stopped. It is to judge.

〔Example〕

Hereinafter, one embodiment of the present invention will be described based on the drawings. 1st
FIG. 1 is a block diagram showing a schematic configuration of an embodiment of the present invention. Reference numeral 1 denotes an imaging means, which is comprised of, for example, a television camera using a CCD imaging device, a vidicon, or the like. 2 is A/D
It is a converting means, which digitizes the image signal obtained by the imaging means 1 to obtain a one-bit or multiple-bit digital signal for each pixel. 3 is a storage means, which stores the digitized image signal. 4 is a spatial differentiation means,
This method performs isotropic, ie direction-independent, differentiation processing on the digitized image signal to obtain the absolute value of the differentiation. For example, as shown in Figure 2, using a 3 x 3 spatial filter, el = 8XE - (A - F B + C +
D+F+G+H+I) is performed. The absolute differential value let becomes large in areas where the grayscale changes are large in the image. Therefore, if the binarization means 5 extracts pixels exceeding a predetermined darkness value, edges can be extracted.

In addition, what is generally called a Laplacian filter may be used as the spatial filter.

6 is a labeling means, and 2 obtained by the binarization means 5
This method labels multiple divided regions of a value image.

7 is a circle detection means, which detects whether each labeled area is circular or not, and if it is determined that it is circular, outputs the circle detection results such as the center coordinates and radius of the circle. be.

Reference numeral 8 denotes a circle detection result storage means, which temporarily stores the circle detection results such as the center coordinates and radius of the circle determined by the circle detection means 7.

Reference numeral 9 denotes a comparison determination means, which determines that a vehicle exists if a circular area exists based on the circle detection result in the current image outputted from the circle detection means 7, and outputs the determination result. Further, the circle detection result in the current image outputted from the circle detection means 7 is compared with the circle detection result in the previous image outputted from the circle detection result storage means 8, and if the center coordinates and radius of the circle match, the vehicle It determines that the system is stopped, and outputs the result of the judgment.

Here, the operation of circle detection will be explained using FIG. The regions labeled by the labeling means 6 are sequentially input, and the peripheral length thereof is calculated as the total number P of pixels forming the boundaries of the regions. Generally, the circumference of a circle is P. is the radius r. Then, P,=2πr0. Therefore, the radius r when the perimeter is P is determined as r=P/2π. Using the template of the circle with the radius r obtained in this way, if the template matching with the area is achieved, the circle detection results such as the center coordinates and radius of the circle are used as the circle detection result. The result is outputted to the result storage means 8 and the comparison/judgment means 9.

This operation is performed for all labeled areas.

FIG. 4 shows a specific example of the circle detection operation. Figure 4(a) shows a case where the labeled area image (portion shown by a solid line) is not circular, and Figure 4(b) shows a case where the labeled area image (portion shown by a solid line) is circular. It shows a case. In each area image, the circular part indicated by the dotted line is
A circular template with a radius r calculated from the perimeter of the solid line portion is shown. In the case of FIG. 4(a), as a result of template matching, the circle template and the boundary of the area match only the hatched portion in the figure, so it is not determined that the area is circular. In the case of FIG. 4(b), as a result of template matching, the circle template and the boundary of the area match over the entire circumference, so it is determined that the area is circular.

[Effects of the Invention] As described above, according to the vehicle detection device of the present invention, the image signal obtained by imaging the monitoring area is digitized, spatially differentiated, binarized, and labeled. By matching each extracted region using a circular template, we are able to detect only the shape of the wheel part, which is a characteristic of the vehicle, that is, the circular region, so only the vehicle can be detected reliably. Furthermore, the circle detection results such as the center coordinates and radius of the detected circular area are stored, and the circle detection results for the previous image and the current image are compared, and -
Since the vehicle is determined to be stopped if the degree of growth is high, a vehicle detection device capable of detecting the stoppage of the vehicle can be provided.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an embodiment of the present invention, FIG. 2 is an explanatory diagram showing an example of a spatial differentiator according to the above, and FIG. 3 is a flowchart showing the operation of circle detection according to the above. FIG. 4 is an explanatory diagram of a specific example of the circle detection operation according to the above. 1...-Imaging means 2...A/D conversion means 3
- Storage means 4- Spatial differentiation means 5... Binarization means 6 - Labeling means Circle detection means Circle detection result storage means Comparison and determination means

Claims (2)

[Claims] (1) Imaging means for photographing a monitoring area and obtaining an image signal;
A/D conversion means for digitizing the image signal obtained by the imaging means, storage means for storing the digitized image data, and spatial differentiation means for calculating the differential absolute value of the output from the storage means. and binarization means for comparing the differential absolute value with a preset threshold value and binarizing the differential absolute value, and
a labeling means for labeling each divided region of the differential image data binarized by the digitization means; a circle detection means for detecting a circular region for each labeled region; A vehicle detection device comprising a comparison determination means for determining the presence of a vehicle based on the output circle detection result. (2) The circle detection means is provided with a function of calculating the center coordinates and radius of the detected circle, and includes a circle detection result storage means for storing circle detection results such as the center coordinates and radius of the circle, and 2. The vehicle detection device according to claim 1, wherein the vehicle detection device determines whether the vehicle has stopped by comparing the circle detection results for the previous image and the circle detection results for the current image output from the detection result storage means.