JP2004206441A - License plate reader - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a license plate reader capable of detecting a vehicle whose license plate could not be read and acquiring information on the vehicle. <P>SOLUTION: When a sensor part 3 detects a vehicle passing a road, a first camera photographs the front face of the vehicle, and a first picture processing part 21 reads the license plate on the front face and acquires number information. Also, a second camera 7 photographs the rear face of the vehicle, and a second picture processing part 22 reads the license plate on the rear face and acquires the number information. A decision part 23 decides whether the number information has been normally acquired. When it is decided that the number information has not been normally acquired, it is judged that the vehicle is a candidate of an illegal vehicle, a picture data accumulating part 31 saves pictures on the front face and the rear face of the vehicle, and a picture data analysis part 33 analyzes the picture of the illegal vehicle and acquires detailed information. A number information accumulating part 32 saves the detailed information. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a license plate reading device capable of detecting a vehicle in which a license plate cannot be read normally and acquiring information on the vehicle.
[0002]
[Prior art]
The conventional license plate reading device includes an imaging unit that captures an image of a license plate of a vehicle, an image recognition unit that reads an image captured by the imaging unit, and a computer that stores data of the recognized license plate. There is a type in which data of a license plate of a vehicle recognized by an image recognition unit based on an image captured by a computer is stored in a computer. For example, Patent Document 1 discloses this type of vehicle license plate reading device.
[0003]
[Patent Document 1]
JP-A-2002-133579 (pages 2-4, FIG. 1)
[0004]
[Problems to be solved by the invention]
However, since the conventional license plate reading device processes only the image of the vehicle whose license plate can be read normally, there is a problem that it is not possible to obtain information on a vehicle whose license plate is incorrect. .
[0005]
The present invention has been made to solve the above-described problems, and has as its object to obtain a license plate reading device capable of detecting a vehicle whose license plate is illegal and acquiring information on the vehicle.
[0006]
[Means for Solving the Problems]
A license plate reading device according to the present invention includes a detection unit that detects a vehicle passing through a road, a photographing unit that photographs a license plate of a vehicle in response to vehicle detection by the detection unit, and an image of a vehicle that is photographed by the photographing unit. Image processing means for obtaining vehicle number information from the vehicle, determining means for determining whether the vehicle is a normal vehicle or a fraudulent vehicle based on the vehicle number information obtained by the image processing means, Image storage means for storing an image of the vehicle determined to be invalid, image analysis means for analyzing the image of the vehicle determined to be unauthorized by the determination means, and obtaining information on the unauthorized vehicle; Number information storage means for storing information on unauthorized vehicles.
[0007]
BEST MODE FOR CARRYING OUT THE INVENTION
Embodiment 1 FIG.
FIG. 1 is a diagram for explaining the operation of the license plate reader according to Embodiment 1 of the present invention. The license plate reading device includes a sensor unit (detection unit) 3, a first camera (photographing unit) 5, a second camera (photographing unit) 7, and a control unit 20. The control unit 20 is connected to a processing device (not shown) that performs image processing and the like. As shown in FIG. 1, the vehicle 1 travels straight on a road 10, and the vehicle 2 travels straight ahead of the vehicle 1 on the road 10. The sensor unit 3 detects a vehicle passing on the road 10, and the monitoring area is indicated by 4. The first camera 5 photographs the front of the passing vehicle, and its photographing area is indicated by 6. The second camera 7 photographs the rear surface of the passing vehicle, and its photographing area is indicated by 8. As the first camera 5 and the second camera 7, a charge-coupled device camera (CCD camera) or the like is used.
[0008]
FIG. 2 is a block diagram of a license plate reader according to Embodiment 1 of the present invention. Elements common to those in FIG. 1 are denoted by the same reference numerals, and description thereof will be omitted. The control unit 20 includes a first image processing unit (image processing unit) 21, a second image processing unit (image processing unit) 22, and a determination unit (determination unit) 23. The control unit 20 is connected to the processing device 30. The processing device 30 acquires and processes information from the control unit 20. The processing device 30 includes an image data storage unit (image storage unit) 31, a number information storage unit (number information storage unit) 32, and an image data analysis unit (image analysis unit) 33. The processing device 30 may acquire and process information from the plurality of control units 20.
[0009]
The first image processing unit 21 acquires the number information of the front of the vehicle from the image of the front of the vehicle taken by the first camera 5. The second image processing unit 22 acquires the number information of the rear surface of the vehicle from the image of the rear surface of the vehicle taken by the second camera 7. The determination unit 23 includes information on the form of the plate of the vehicle, and the number information on the front surface of the vehicle obtained by the first image processing unit 21 and the number information on the rear surface of the vehicle obtained by the second image processing unit 22. Based on the above, it is determined whether the vehicle is a normal vehicle or a candidate for a fraudulent vehicle. For example, a vehicle to which either or both of the front and rear license plates are not attached or a vehicle in which the license plate is hidden is determined as a candidate for an unauthorized vehicle.
[0010]
The image data storage unit 31 stores the image of the vehicle determined to be a candidate for an unauthorized vehicle by the determination unit 23, that is, the image captured by the first camera 5 and the image captured by the second camera 7. save. The image data analysis unit 33 analyzes the image data of the vehicle determined as a candidate for a fraudulent vehicle by the determination unit 23, and acquires detailed information (described later) of the fraudulent vehicle. The number information storage unit 32 stores the number information of the vehicle determined to be a normal vehicle by the determination unit 23 and the information of the unauthorized vehicle acquired by the image data analysis unit 33.
[0011]
FIG. 3 is a flowchart showing the operation of the license plate reading device according to the first embodiment. The operation of the license plate reading device will be described with reference to FIGS.
When detecting the vehicle passing through the road (step ST100), the sensor unit 3 notifies the first camera 5 and the second camera 7 of the detection. In response to the vehicle detection notification from the sensor unit 3, the first camera 5 photographs the front of the vehicle (step ST101), and the first image processing unit 21 captures the front of the vehicle. Is read to obtain the number information (step ST102). Further, in response to the notification of vehicle detection from the sensor unit 3, the second camera 7 photographs the rear surface of the vehicle (step ST103), and the second image processing unit 22 is photographed by the second camera 7. Then, the license plate on the rear side is read to acquire license information (step ST104).
[0012]
Subsequently, the determination unit 23 determines whether the first image processing unit 21 has successfully acquired the number information (step ST105). If it is determined that the number information has been normally obtained, the determination unit 23 determines whether the second image processing unit 22 has successfully obtained the number information (step ST106). When it is determined that the image information has been normally obtained, the determination unit 23 further compares the number information obtained by the first image processing unit 21 with the number information obtained by the second image processing unit 22 (step ST107). ), If they match, it is determined that the vehicle is normal. The number information of the normal vehicle is stored in the number information storage unit 32 (step ST108).
[0013]
If it is determined in step ST105 or ST106 that the front or rear number information is not normal, or if it is determined in step ST107 that the front and rear number information do not match, it is determined that the vehicle is a candidate for an unauthorized vehicle. It is determined, and the image data storage unit 31 stores the images of the front and rear surfaces of the vehicle (step ST109). Further, the image data analysis unit 33 analyzes the image and acquires detailed information (step ST110). The image data storage unit 31 notifies the acquired detailed information to the number information storage unit 32, and the number information storage unit 32 stores this information (step ST111).
[0014]
The image data analysis unit 33 may perform the following process in order to obtain detailed information of a vehicle determined to be a fraudulent vehicle candidate. In other words, as a result of analyzing an image of a fraudulent vehicle, if it is determined that the vehicle has a hidden number, the color, shape and size of the body part of the vehicle are acquired from the image, and the number is obtained as fraudulent vehicle information. The information storage unit 32 is notified. Similarly, when a vehicle without both the front and rear license plates is detected, the color, shape, and size of the body of the vehicle are acquired and reported to the license information storage unit 32 as unauthorized vehicle information. When a vehicle to which either one of the front and rear license plates is not detected is detected, the obtained number information is notified to the number information storage unit 32. If a fraudulent vehicle having different license plates attached to the front and rear surfaces is detected, the color, shape, and size of the body part of the vehicle and the acquired front and rear number information are notified to the number information storage unit 32. I do.
[0015]
As described above, according to the first embodiment, the first camera photographs the front of the passing vehicle, the second camera photographs the rear of the passing vehicle, and the number information of the front or the rear is normally acquired. If it was not possible, or if the front and rear number information did not match, the image was analyzed to obtain detailed information on the vehicle, so only the number information of the vehicle with a normal license plate was used. In addition, detailed information of an unauthorized vehicle can be stored, and an effect that can be used for searching for a criminal vehicle or the like can be obtained.
[0016]
Also, when a vehicle without either the front or the rear license plate is detected, the obtained license information is saved. This information is used to provide appropriate guidance to the vehicle owner. It can be performed.
[0017]
Embodiment 2 FIG.
In the second embodiment, a function for identifying a motorcycle is added to the determination unit 23 shown in FIG. For this reason, the determination unit 23 is provided with information that can distinguish between the plate of the motorcycle and the plate of the automobile, for example, information on the form of the plate of the motorcycle. FIG. 4 is a flowchart showing the operation of the license plate reader according to the second embodiment. The operation of the license plate reader will be described with reference to FIGS.
[0018]
As in the first embodiment, when the sensor unit 3 detects a vehicle passing through a road (step ST200), the first camera 5 captures a front surface of the vehicle in response to the vehicle detection of the sensor unit 3 (step ST200). ST201), the first image processing unit 21 reads the front license plate photographed by the first camera 5, and acquires the license information (step ST202). In addition, in response to the vehicle detection of the sensor unit 3, the second camera 7 photographs the rear surface of the vehicle (step ST203), and the second image processing unit 22 records the number of the rear surface photographed by the second camera 7. The plate is read to obtain the number information (step ST204).
[0019]
Subsequently, the determination unit 23 determines whether or not the first image processing unit 21 has successfully obtained the number information on the front surface (step ST205). It is determined whether the number information on the rear surface has been normally acquired by the second image processing unit 22 (step ST206). When it is determined that the image information has been normally obtained, the determining unit 23 further compares the number information obtained by the first image processing unit 21 with the number information obtained by the second image processing unit 22 (step ST207). ), If they match, it is determined that the vehicle is normal. The number information of the normal vehicle is stored in the number information storage unit 32 (step ST208).
[0020]
If it is determined in step ST205 or ST206 that the number information on the front surface or the rear surface is not normal, the determination unit 23 determines the number information (step ST209). That is, the number information of the front surface acquired by the first image processing unit 21 is not normal, and the number information of the rear surface acquired by the second image processing unit 22 and the plate information of the motorcycle owned by the determination unit 23 are different. If there is a match, the vehicle is determined to be a normal motorcycle, and the number information of the vehicle is stored in the number information storage unit 32 (step ST208). If the above conditions are not satisfied in step ST209, or if it is determined in step ST207 that the number information on the front and rear surfaces does not match, it is determined that the vehicle is a fraudulent vehicle, and the image is stored as image data as in the first embodiment. The section 31 stores the information (step ST210), the image data analysis section 33 analyzes and acquires detailed information (step ST211), and the number information storage section 32 stores the detailed information (step ST212).
[0021]
As described above, according to the second embodiment, it is determined that the number information of the front surface acquired by the first image processing unit 21 is not normal and the number information of the rear surface acquired by the second image processing unit 22. When the plate information of the motorcycle owned by the unit 23 is identical to the motorcycle, the determination unit 23 determines that the vehicle is a normal motorcycle. Therefore, the number is also read for the motorcycle. The effect that can be obtained is obtained.
[0022]
Embodiment 3 FIG.
FIG. 5 is a block diagram of a license plate reader according to Embodiment 3 of the present invention. Elements common to those in FIG. 2 are denoted by the same reference numerals, and description thereof will be omitted. In the third embodiment, a noise measurement function is added to the sensor unit 3 of the first embodiment, and the measurement result is notified to the determination unit 23. The determination unit 23 has information on the noise reference value.
[0023]
FIG. 6 is a flowchart showing the processing of the license plate reading device according to the third embodiment. The operation of the license plate reading device will be described with reference to FIGS.
When detecting the vehicle passing through the road (step ST300), the sensor unit 3 measures the noise of the vehicle (step ST301) and notifies the determination unit 23 of the measurement result. In response to the vehicle detection by the sensor unit 3, the first camera 5 captures an image of the front of the vehicle (step ST302), and the first image processing unit 21 displays the front license plate captured by the first camera 5. It reads and obtains number information (step ST303). Further, in response to the vehicle detection of the sensor unit 3, the second camera 7 photographs the rear surface of the vehicle (step ST304), and the second image processing unit 22 captures the rear surface number photographed by the second camera 7. The plate is read, and the number information is obtained (step ST305).
[0024]
Subsequently, the determination unit 23 determines whether the first image processing unit 21 has successfully acquired the front-side number information (step ST <b> 306). It is determined whether the number information on the rear side has been normally acquired by the second image processing unit 22 (step ST307). When it is determined that the image information has been normally obtained, the determining unit 23 further compares the number information obtained by the first image processing unit 21 with the number information obtained by the second image processing unit 22 (step ST308). ), If they match, it is determined that the vehicle is normal. Subsequently, the determination unit 23 determines whether or not the noise measurement result notified from the sensor unit 3 exceeds a reference value (step ST309). If not, the determination unit 23 determines that the vehicle is a normal vehicle, and determines that the vehicle is normal. The number information is stored in the number information storage unit 32 (step ST310).
[0025]
If it is determined in step ST306 or step ST307 that the front or rear number information is not normal, or if it is determined in step ST308 that the front and rear number information do not match, it is determined that the vehicle is a candidate for an unauthorized vehicle. The image data storage unit 31 stores the images of the front and rear surfaces of the vehicle (step ST311), and the image data analysis unit 33 analyzes and obtains detailed information as in the first embodiment (step ST312). ). The image data storage unit 31 notifies the acquired detailed information to the number information storage unit 32, and the number information storage unit 32 stores this information (step ST313). If it is determined in step ST309 that the noise emitted by the vehicle exceeds the reference value, it is determined that the vehicle is a fraudulent vehicle, and the number information storage unit 32 includes information indicating that the noise exceeds the reference value. The number information is stored (step ST313).
[0026]
As described above, according to the third embodiment, the sensor unit 3 measures the noise of the vehicle passing through the road, and if the measurement result exceeds the reference value, the determination unit 23 determines that the vehicle is an unauthorized vehicle. As a result, an effect of detecting a vehicle emitting noise exceeding the reference value can be obtained.
[0027]
In addition, the function of identifying the motorcycle shown in the second embodiment may be added to the determination unit 23 of the third embodiment.
[0028]
【The invention's effect】
As described above, according to the present invention, a license plate reading device detects a vehicle passing through a road, a photographing device photographing a license plate of a vehicle in response to vehicle detection by the detecting device, and a photographing device. Image processing means for obtaining vehicle number information from an image of a vehicle taken by the vehicle, and determining means for determining whether the vehicle is a normal vehicle or an unauthorized vehicle based on the vehicle number information obtained by the image processing means. Image storage means for storing an image of a vehicle determined to be a fraudulent vehicle by the determination means; image analysis means for analyzing an image of a vehicle determined to be a fraudulent vehicle by the determination means to obtain information on the fraudulent vehicle; A license information storage unit for storing information on the unauthorized vehicle acquired by the analysis unit, so that the license plate detects the unauthorized vehicle, and There is an effect that it is possible to obtain information.
[Brief description of the drawings]
FIG. 1 is a diagram illustrating the operation of a license plate reading device according to a first embodiment of the present invention.
FIG. 2 is a block diagram of a license plate reading device according to Embodiment 1 of the present invention.
FIG. 3 is a flowchart showing an operation of the license plate reading device according to the first embodiment of the present invention.
FIG. 4 is a flowchart showing an operation of the license plate reading device according to the second embodiment of the present invention.
FIG. 5 is a block diagram of a license plate reading device according to a third embodiment of the present invention.
FIG. 6 is a flowchart showing the operation of the license plate reading device according to Embodiment 3 of the present invention.
[Explanation of symbols]
1, 2 vehicle, 3 sensor unit (detection means), 4 monitoring area of sensor unit 3, 5 first camera (photographing means), 6 photographing area of first camera, 7 second camera (photographing means), 8 shooting area of the second camera, 10 road, 20 control unit, 21 first image processing unit (image processing unit), 22 second image processing unit (image processing unit), 23 determination unit (determination unit), 30 processing device, 31 image data storage unit (image storage unit), 32 number information storage unit (number information storage unit), 33 image data analysis unit (image analysis unit).

Claims (5)

Detecting means for detecting a vehicle passing through the road;
Photographing means for photographing a license plate of the vehicle in response to vehicle detection by the detecting means;
Image processing means for acquiring vehicle number information from an image of the vehicle taken by the photographing means,
A determination unit configured to determine whether the vehicle is a normal vehicle or an unauthorized vehicle based on the vehicle number information obtained by the image processing unit;
An image storage unit that stores an image of a vehicle that has been determined to be a fraudulent vehicle by the determination unit;
A license plate reading device comprising: license information storage means for storing information on a fraudulent vehicle acquired by the image analysis means. Detecting means for detecting a vehicle passing through the road;
Photographing means for photographing a license plate before and after the vehicle in response to vehicle detection by the detecting means,
Image processing means for acquiring front and rear number information from an image of a vehicle taken by the photographing means,
The image processing means compares the information before and after the acquisition, if at least one is not normal number information, or if the number information before and after do not match, determine that the vehicle is an unauthorized vehicle, the number information before and after both A license plate reading device comprising: determination means for determining that the vehicle is a normal vehicle when the number information is normal and the number information before and after matches. 2. The vehicle according to claim 1, wherein the determination unit determines that the vehicle is a normal motorcycle when the number information on the front surface is not normal and the number information on the rear surface matches the number information of the motorcycle. The license plate reader according to claim 2. 4. The image analysis unit according to claim 1, wherein the color, shape, and size of the vehicle body are acquired from an image of the vehicle determined to be a fraudulent vehicle by the determination unit. 5. License plate reader. The detection means measures the noise of the passing vehicle and notifies the measurement result to the determination means, and the determination means compares the measurement result with the reference value, and if the measurement result exceeds the reference value, it is determined that the vehicle is an unauthorized vehicle. The license plate reader according to any one of claims 1 to 4, wherein the license plate is read.

Images