JPH04354100A - Car type discriminator - Google Patents

Abstract

PURPOSE:To extremely decrease the probability of erroneously discriminating a car type by discriminating a bus or a truck especially even when information on a number plate can not be read. CONSTITUTION:An image pickup device 4 pickes up the front image of an approaching car. When a car detector 3 detects the approaching car, an image processing part 5 fetches the front image of the car picked up by the image pickup device 4, extracts the feature information of the car by executing image processings such as smoothing, differentiation and binarizing or the like and discriminates the car type by collating this feature information with a reference pattern previously stored in a dictionary memory.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a vehicle type discrimination device for determining the type of automobile on a toll road or a toll parking lot, for example.

0002

2. Description of the Related Art Generally, for example, at a toll gate on a toll road, an attendant performs the task of collecting tolls. In this case, if the type of vehicle (automobile) can be automatically identified,
It is thought that it will be possible to automate these tasks, and conventionally,
The following vehicle type discrimination method has been proposed.

In other words, it detects the number of vehicle axles, tread, vehicle length, vehicle height, tire width (single/double), size of the license plate, information on lowercase letters on the license plate, etc. The vehicle type is then determined from this information.

0004

[Problems to be Solved by the Invention] However, the above-mentioned conventional vehicle type discrimination method has the following problems. That is, if the information on the license plate cannot be read, the discrimination between a bus and a truck may not be performed correctly, resulting in erroneous discrimination. Furthermore, if the license plate is covered with dirt or snow, it may not be recognized or may be recognized incorrectly.

[0005] Therefore, the present invention provides a vehicle type identification device that is capable of identifying buses, trucks, etc. even when the information on the license plate cannot be read, and the possibility of misidentifying the vehicle type is significantly reduced. The purpose is to

[0006]

[Means for Solving the Problems] The vehicle type discrimination device of the present invention includes: an imaging means for taking a one-sided image of a vehicle; a feature extraction means for extracting characteristic information of the vehicle from the image taken by the imaging means; The vehicle includes determining means for determining the type of vehicle by comparing the characteristic information extracted by the characteristic extracting means with reference information set in advance.

[0007]

[Operation] For example, by capturing the front image of a vehicle and using image processing to extract the characteristics of a bus or truck, and obtaining information for identifying the vehicle type, even if the information on the license plate cannot be read. , it becomes possible to identify buses, trucks, etc. based on the characteristics of the front of the vehicle, and the possibility of misidentifying the vehicle type is significantly reduced.

[0008]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings.

FIG. 2 shows an example of the arrangement of the imaging means in the vehicle type discrimination device according to this embodiment. In the figure,
Reference numeral 1 denotes a travel path at the entrance gate of a toll gate of a toll road, for example, and a vehicle (automobile) 2 entering the entrance gate travels in the direction of the arrow shown in the figure. Vehicle detectors 3 that optically detect incoming vehicles 2 are installed on both sides of the traveling path 1. In front of the vehicle detector 3 and on one side of the travel path 1, an imaging device 4 is installed to capture a front image of the incoming vehicle 2. The imaging device 4 is, for example,
It consists of an industrial television camera and a strobe light emitting device.

FIG. 1 shows the configuration of a vehicle type discrimination device according to this embodiment. That is, each output of the vehicle detector 3 and the imaging device 4 is supplied to the image processing section 5, respectively. The image processing unit 5 controls the imaging device 4, and
By accepting the output of the imaging device 4 and performing image processing as described later, vehicle type information is output. Image processing section 5
The vehicle type information output from the vehicle type determination section 6 is supplied to the vehicle type determination section 6.

The vehicle type discriminator 6 uses other vehicle type information obtained by conventionally known means (for example, the number of vehicle axles, tread, vehicle length, vehicle height, tire width, size of the license plate, information on the license plate, etc.). information, etc.) 7 and the vehicle type information output from the image processing unit 5, determine the final vehicle type,
The vehicle type information is sent to the automatic ticket issuing machine 8.

Next, the operation of such a configuration will be explained with reference to the flowchart shown in FIG. Now, when the vehicle 2 enters and the vehicle detector 3 detects it,
The vehicle detection signal is sent to the image processing section 5. Upon receiving the vehicle detection signal, the image processing section 5 sends a strobe light emission command signal to the imaging device 4. Upon receiving the strobe light emission command signal, the imaging device 4 operates the strobe light emitting device in synchronization with the shutter, and sends a freeze signal to the image processing unit 5.

[0013] Upon receiving the freeze signal, the image processing unit 5 takes in the image information of the field at that timing output from the imaging device 4, and performs the following image processing. That is, first, the captured image information is A/D converted and stored in the internal frame memory. The contents of this frame memory (original image) are, for example, as shown in FIG. 3(a).

Next, the image information stored in the frame memory is smoothed to remove noise, and then processing such as differentiation (edge detection) is performed to obtain a differential image as shown in FIG. 3(b). Next, by binarizing this differential image with an appropriate threshold, as shown in FIG. 3(c),
Generates a binarized image that highlights windows and external shapes.

Next, this binarized image is normalized. The reason for performing this normalization process is that the position and size of the vehicle 2 change when the vehicle 2 runs on the right side of the screen or on the left side of the screen. Next, by comparing this normalized binarized image with a reference pattern previously stored in a dictionary memory (not shown),
It calculates the degree of similarity, determines whether it is a bus or a truck, and outputs vehicle type information based on the determination result.

In this way, the vehicle type information output from the image processing section 5 is sent to the vehicle type discriminating section 6. Then, the vehicle type discrimination unit 6 collects other vehicle type information (for example, the number of vehicle axles, tread, vehicle length, vehicle height,
The final vehicle type is determined based on the tire width, the size of the license plate, information on the license plate, etc.) 7 and the vehicle type information output from the image processing section 5, and the vehicle type information based on the determination result is output. This output vehicle type information is sent to the automatic pass ticket issuing machine 8 and printed on the issued pass ticket.

[0017] In this way, by capturing an image of the front of a vehicle and using image processing to extract the characteristics of a bus, truck, etc., and obtaining information for identifying the vehicle type, even if the information on the license plate cannot be read. Even in the case of a vehicle, it is now possible to easily identify a bus, truck, etc. based on the characteristics of the front of the vehicle (for example, the shape and position of the windshield), and the possibility of misidentifying the vehicle type is significantly reduced.

[0018] In the above embodiment, a case has been described in which the characteristics of the vehicle are extracted from the front image of the vehicle, but the invention is not limited to this. May be extracted.

Further, in the above embodiment, the case where the present invention is applied to a vehicle type discriminating device for discriminating the vehicle type on a toll road has been described, but the present invention is not limited to this. It can also be applied to a vehicle type discrimination device that discriminates the type of vehicle.

[0020]

[Effects of the Invention] As detailed above, according to the present invention, even if the information on the license plate cannot be read, it is possible to identify buses, trucks, etc., thereby eliminating the possibility of misidentification of the vehicle type. It is possible to provide a vehicle type discrimination device that significantly reduces the number of vehicle types.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing the configuration of a vehicle type discrimination device according to an embodiment of the present invention.

FIG. 2 is a perspective view showing an example of the arrangement of imaging means at the entrance gate of a toll gate of a toll road.

FIG. 3 is a flowchart explaining image processing.

[Explanation of symbols]

1... Driving route, 2... Vehicle, 3... Vehicle detector, 4...
Imaging device, 5... image processing section, 6... vehicle type discrimination section, 7...
...Other car information.

Claims (1)

[Claims] Claims: 1. An image capturing means for capturing a one-sided image of a vehicle; a feature extracting means for extracting characteristic information of the vehicle from the image captured by the image capturing means; A vehicle type discriminating device comprising: discriminating means for discriminating the vehicle type of the vehicle by comparing it with set reference information.