JP2016095733A - Vehicle monitoring system and vehicle monitoring method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To monitor a fraudulent action of various kinds of vehicles passing a lane for automatic toll collection.SOLUTION: In a vehicle monitoring system 10, a first camera 12 captures an image in a direction where there is an entrance of a lane 30 from a location L1 closer to an exit than the entrance of the lane 30, a second camera 13 captures an image in a direction where there is the exit of the lane 30 from a location L2 closer to the entrance than the exit of the lane 30, a first sensor 14 detects a vehicle entering the lane 30, a second sensor 15 detects a vehicle exiting from the lane 30, and a control device 20 records an entering image P1 which is an image captured by the first camera 12 when the first sensor 14 detects a vehicle entering the lane 30 and an exiting image P2 which is an image captured by the second camera 13 when the second sensor 15 detects a vehicle exiting from the lane 30.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a vehicle monitoring system and a vehicle monitoring method.

  In the ETC (registered trademark) lane unauthorized traffic prevention system, a near-infrared light strobe is emitted using a signal that detects the release state of the gate bar when the vehicle breaks through the start control machine with the gate bar attached as a trigger. The vehicle is imaged with a black and white camera. The release state of the gate bar is a state where the gate bar is opened.

  When imaging illegal traffic vehicles using a signal that detects the release state of the gate bar, the gate bar has been opened, such as a duck driving in which a small vehicle passes to hide behind a large vehicle, or illegal traffic in which a motorcycle scratches the gate bar. Unauthorized traffic without an event cannot be detected.

  In addition, when shooting a vehicle by emitting a near-infrared strobe for night imaging, because it is black-and-white imaging, information such as the color of the vehicle and the color of the license plate is obtained as information on the characteristics of the illegally passing vehicle. I can't. For this reason, a great deal of labor is required for identifying a vehicle or a driver who performs unauthorized traffic multiple times.

  2. Description of the Related Art Conventionally, there is a technique for photographing a gate bar in color at a predetermined time interval and strobe photographing a vehicle and a gate bar based on a signal that detects the release state of the gate bar (see, for example, Patent Document 1).

JP 2009-252093 A

  In the prior art, since only the front part of the vehicle is photographed, there is a problem that the license plate at the rear part of the vehicle cannot be confirmed from the photographed image. To monitor the fraud of various vehicles, such as unauthorized vehicles that replace only the front number plate, which is easier to remove than the rear number plate, or motorcycles that have a number plate only at the rear, both front and rear of the vehicle It is necessary to check the license plate.

  An object of the present invention is, for example, to monitor fraud in various vehicles passing through a lane for automatic fee collection.

A vehicle monitoring system according to one aspect of the present invention includes:
A first camera that captures an image of the direction of the entrance of the lane from a location closer to the exit than the entrance of the lane for automatic fee collection;
A second camera that captures an image of the direction of the exit of the lane from a location closer to the entrance than the exit of the lane;
A sensor for detecting a vehicle entering the lane and a vehicle exiting the lane;
An approach image, which is an image taken by the first camera when a vehicle entering the lane is detected by the sensor, and the second image when a vehicle exiting the lane is detected by the sensor. A recording unit that records an exit image that is an image captured by the camera.

  In the present invention, since the entrance image and the exit image of the vehicle passing through the lane for automatic fee collection are recorded, it is possible to confirm both the front and rear license plates from the image. Therefore, according to the present invention, it is possible to monitor fraud of various types of vehicles.

1 is a diagram illustrating a configuration of a vehicle monitoring system according to a first embodiment. 1 is a block diagram showing a configuration of a control device for a vehicle monitoring system according to Embodiment 1. FIG. 3 is a flowchart showing the operation of the control device of the vehicle monitoring system according to the first embodiment. FIG. 3 is a diagram illustrating an example of a hardware configuration of a control device of the vehicle monitoring system according to the first embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In addition, the same code | symbol is attached | subjected to the part which is the same or it corresponds in each figure. In the description of the embodiments, the description of the same or corresponding parts will be omitted or simplified as appropriate.

Embodiment 1 FIG.
In this embodiment, lighting that can obtain sufficient illuminance for color imaging is installed even at night at toll gates and billing points on the road, two laser sensors are arranged upstream and downstream, and the vehicle travels further The entire image of the vehicle is captured in color from the front and rear with respect to the direction. The timing of entry and exit of the vehicle is detected at the irradiation point of the laser sensor, the average speed of the vehicle is obtained from the time difference between the detections of the upstream and downstream laser sensors, and the shape of the passing vehicle is normalized according to the speed. Thereby, while distinguishing the vehicle type of the vehicle to pass, the color image before and behind for every vehicle to pass is obtained, respectively. When automatic fee collection is performed at the vehicle detection timing and charging is not performed normally, the vehicle is recorded as an illegal passing vehicle. Since it is possible to confirm the driver's seat and the license plate of the vehicle from the obtained image, it becomes easy to specify an unauthorized passing vehicle.

  Hereinafter, the configuration of the system according to the present embodiment, the operation of the system according to the present embodiment, and the effects achieved by the present embodiment will be described in order.

*** Explanation of configuration ***
FIG. 1 is a diagram showing a configuration of a vehicle monitoring system 10 that is a system according to the present embodiment. FIG. 2 is a block diagram illustrating a configuration of the control device 20 of the vehicle monitoring system 10.

  As shown in FIG. 1, the vehicle monitoring system 10 includes a lighting device 11, a first camera 12, a second camera 13, a first sensor 14, a second sensor 15, a wireless unit 16, and a control device 20. . Although not shown, the vehicle monitoring system 10 further includes a start controller to which a gate bar is attached.

  As illustrated in FIG. 2, the control device 20 includes a detection unit 21, a recording unit 22, a determination unit 23, and a fusion unit 24. That is, the vehicle monitoring system 10 includes a detection unit 21, a recording unit 22, a determination unit 23, and a fusion unit 24 as a part of the control device 20.

  The vehicle monitoring system 10 is installed in a lane 30 for automatic fee collection. Note that the control device 20 may be installed in a remote place such as a data center. Alternatively, a part of the control device 20 may be installed in a remote place such as a data center as another device.

  The illumination device 11 irradiates white light from above the lane 30 toward the road surface of the lane 30. The illumination device 11 includes an LED (light emitting diode) as a light source. In addition, the illuminating device 11 may be provided with types of light sources other than LED, such as a discharge lamp and organic EL (organic electroluminescence), as a light source. The purpose of the lighting device 11 is to improve the visibility of the driver of the vehicle to pass mainly at night and other times when the amount of sunlight is small, or to improve the visibility of the staff if the toll gate is manned. Is not lit only when the vehicle is photographed.

  The first camera 12 is installed at a location L 1 closer to the exit than the entrance of the lane 30. The first camera 12 captures an image in a direction in which the entrance of the lane 30 is located from the installed location L1. The first camera 12 captures a color image using light emitted from the illumination device 11 at least at night. The first camera 12 captures a color image using sunlight when the lighting device 11 is not lit.

  The second camera 13 is installed at a location L 2 that is closer to the entrance than the exit of the lane 30. The second camera 13 captures an image in a direction in which the exit of the lane 30 is located from the installed location L2. The second camera 13 captures a color image using light emitted from the lighting device 11 at least at night. The second camera 13 captures a color image using sunlight when the lighting device 11 is not lit.

  The first sensor 14 is installed on the left side above the lane 30. The first sensor 14 detects a vehicle entering the lane 30. Examples of the vehicle include an automobile 31 and a motorcycle 32. The first sensor 14 further detects the shape of the vehicle passing through the lane 30. The first sensor 14 transmits a signal indicating the presence of the vehicle and the detection result of the shape of the vehicle to the detection unit 21. This signal is transmitted as soon as the presence of the vehicle is detected.

  The second sensor 15 is installed on the right above the lane 30. The second sensor 15 detects a vehicle leaving the lane 30. The second sensor 15 further detects the shape of the vehicle passing through the lane 30. The second sensor 15 transmits a signal indicating the presence of the vehicle and the detection result of the shape of the vehicle to the detection unit 21. This signal is transmitted as soon as the presence of the vehicle is detected.

  The first sensor 14 may be installed on the right side above the lane 30, and in this case, the second sensor 15 is preferably installed on the left side above the lane 30. By disposing the first sensor 14 and the second sensor 15 in the left-right direction, the shape of the vehicle can be determined with high accuracy from the shape detection results of the first sensor 14 and the second sensor 15. It becomes possible to do.

  Each of the first sensor 14 and the second sensor 15 is a laser sensor, which emits a laser beam toward the road surface of the lane 30 and scans the lane 30 in the width direction. The shape of the vehicle is detected. The shape of the vehicle is represented as laser point cloud data. Note that the first sensor 14 and the second sensor 15 may be other types of sensors such as a camera.

  In the present embodiment, the sensors that detect the vehicle that enters the lane 30 and the vehicle that leaves the lane 30 are divided into the first sensor 14 and the second sensor 15, but one laser is mounted. It may be implemented by a sensor or other type of sensor.

  The wireless unit 16 performs wireless communication for automatic toll collection with the on-vehicle device of the vehicle passing through the lane 30 and generates charging information E that is information indicating whether charging has been normally performed. The billing information E may include data collected from the vehicle-mounted device. Since communication is impossible when there is no on-vehicle device, in that case, the charging information E may include data indicating that communication is not possible.

  The detection unit 21 receives signals transmitted from the first sensor 14 and the second sensor 15. The detection unit 21 causes the first camera 12 to capture an image at the timing when the first sensor 14 receives a signal indicating that a vehicle entering the lane 30 has been detected, and the wireless unit 16 collects automatic charges. Wireless communication. That is, the detection unit 21 causes the first camera 12 to take an image when the first sensor 14 detects a vehicle entering the lane 30 and performs wireless communication for automatic fee collection to the wireless unit 16. Make it. The detection unit 21 causes the second camera 13 to capture an image at the timing when the second sensor 15 receives a signal indicating that the vehicle leaving the lane 30 has been detected. That is, the detection unit 21 causes the second camera 13 to capture an image when the second sensor 15 detects a vehicle leaving the lane 30.

  Note that the first camera 12 may always take an image regardless of the detection result of the first sensor 14. That is, the first camera 12 may capture a moving image. Similarly, the second camera 13 may always take an image regardless of the detection result of the second sensor 15. That is, the second camera 13 may capture a moving image.

  The detection unit 21 further generates shape information F that is information indicating the shape detected by at least one of the first sensor 14 and the second sensor 15. Specifically, the detection unit 21 estimates the speed of the vehicle from the time difference in timing when the vehicle is detected by the first sensor 14 and the second sensor 15. The detection unit 21 normalizes the shapes detected by the first sensor 14 and the second sensor 15 according to the estimated speed. The detection unit 21 generates information indicating the normalized shape as the shape information F. The detecting unit 21 may simply generate information indicating the shape detected by either the first sensor 14 or the second sensor 15 as the shape information F.

  The recording unit 22 exits from the lane 30 by the second sensor 15 and the approach image P1 that is an image taken by the first camera 12 when the first sensor 14 detects a vehicle entering the lane 30. When the vehicle to be detected is detected, an exit image P2 that is an image captured by the second camera 13 is recorded. In the present embodiment, the recording unit 22 records color images as the approach image P1 and the exit image P2. Here, “recording” means writing to a recording medium such as a memory.

  The determination unit 23 acquires the billing information E generated by the wireless unit 16. When the charging information E indicates that charging has not been performed normally, the determination unit 23 determines that the vehicle that has passed through the lane 30 is an unauthorized vehicle.

  The determination unit 23 further reads the entry image P1 and the exit image P2 recorded by the recording unit 22. And the determination part 23 extracts the information described in the number plate of the vehicle reflected in the approach image P1 recorded by the recording part 22 as front part number plate information N1. Moreover, the determination part 23 extracts the information described in the number plate of the vehicle reflected in the exit image P2 recorded by the recording part 22 as the rear part number plate information N2. The determination unit 23 determines whether the vehicle that has passed through the lane 30 is an unauthorized vehicle based on the extraction result of the front license plate information N1 and the rear license plate information N2. Here, “the extraction result of the front license plate information N1 and the rear license plate information N2” means whether or not the front license plate information N1 has been extracted, and if so, the contents of the front license plate information N1. Information indicating whether or not the rear license plate information N2 has been extracted, and if so, the contents of the rear license plate information N2. If the vehicle license plate is not shown in the approach image P1, the determination unit 23 does not extract the front license plate information N1. If the number plate of the vehicle is not shown in the exit image P2, the determination unit 23 does not extract the rear number plate information N2.

  Specifically, the determination unit 23 indicates that charging has been normally performed by the charging information E, and the lane 30 passes when the front license plate information N1 and the rear license plate information N2 match. The determined vehicle is not an unauthorized vehicle. The determination unit 23 may determine that the vehicle passing through the lane 30 is not an unauthorized vehicle even when the front license plate information N1 and the rear license plate information N2 do not match. In the present embodiment, the determination unit 23 acquires the shape information F generated by the detection unit 21. Then, the determination unit 23 determines the type of the vehicle that has passed through the lane 30 from the shape detected by at least one of the first sensor 14 and the second sensor 15 indicated by the shape information F. The determination unit 23 determines whether the vehicle that has passed through the lane 30 is an unauthorized vehicle based on the determination result of the type in addition to the extraction result of the front license plate information N1 and the rear license plate information N2.

  As types of vehicles, there are automobiles 31 including large automobiles such as small cars, ordinary automobiles, and buses, and motorcycles 32, automobiles connected to tow vehicles such as tow trailers, and the like. The motorcycle 32 normally does not have a license plate at the front and has a license plate only at the rear. Therefore, when the determination unit 23 determines that the vehicle that has passed through the lane 30 is the motorcycle 32, the determination unit 23 extracts the rear license plate information N2 even if the front license plate information N1 is not extracted. If the information E indicates that the charging can be performed normally, it is determined that the vehicle is not an unauthorized vehicle. In addition, an automobile to which a tow vehicle is connected usually has no license plate at the rear and a license plate only at the front, or the number written on the front license plate and the number on the rear. The number is different. Therefore, if the determination unit 23 determines that the vehicle passing through the lane 30 is an automobile to which the towing vehicle is connected, the determination unit 23 has not extracted the rear license plate information N2, or the front license plate information N1 and the rear license number Even if the plate information N2 does not match, if the front license plate information N1 is extracted and the billing information E indicates that the billing can be normally performed, it is determined that the vehicle is not an unauthorized vehicle. To do. On the other hand, when the determination unit 23 determines that the vehicle passing through the lane 30 is the automobile 31, it does not extract at least one of the front license plate information N1 and the rear license plate information N2, or the front If the part number plate information N1 and the rear part number plate information N2 do not match, it is determined that the vehicle is an unauthorized vehicle even if the billing information E indicates that billing can be performed normally.

  The determination unit 23 determines, at least for the vehicle determined to be an unauthorized vehicle, the charging information E, the shape information F, the entry image P1, the exit image P2, the front license plate information N1, and the rear license plate information N2. Is output.

  For the vehicle determined to be at least a fraudulent vehicle, the fusion unit 24 outputs the billing information E, the shape information F, the entry image P1, the exit image P2, and the front license plate information N1 output from the determination unit 23. The rear license plate information N2 and the passage history information are collected and stored in the database. The fusion unit 24 may output the traffic history information to the host device, and in this case, the host device stores the traffic history information in the database.

*** Explanation of operation ***
FIG. 3 is a flowchart illustrating an example of the operation of the control device 20. The operation of the control device 20 corresponds to the vehicle monitoring method according to the present embodiment. The operation of the control device 20 corresponds to the processing procedure of the program according to the present embodiment.

  In the detection process of step S <b> 1, the detection unit 21 receives the signal transmitted from the first sensor 14 or the second sensor 15 and generates the shape information F.

  In the photographing process in step S2, the detection unit 21 causes the first camera 12 to photograph the approach image P1 in accordance with the signal received from the first sensor 14 in step S1. Or the detection part 21 makes the 2nd camera 13 image | photograph the leaving image P2 according to the signal received from the 2nd sensor 15 by step S1.

  In the recording process of step S3, the recording unit 22 records the approach image P1 captured by the first camera 12 in step S2. Alternatively, the recording unit 22 records the exit image P2 captured by the second camera 13 in step S2.

  If a signal indicating that the first sensor 14 has detected a vehicle entering the lane 30 is received in step S1, the process proceeds to step S4. Note that step S4 is preferably executed immediately after step S1, not after step S3. If a signal indicating that the second sensor 15 has detected a vehicle leaving the lane 30 is received in step S1, the process proceeds to step S5.

  In the communication process of step S4, the wireless unit 16 generates billing information E by performing wireless communication for automatic toll collection with the vehicle-mounted device passing through the lane 30.

  In the determination process of step S5, the determination unit 23 extracts the front license plate information N1 and the rear license plate information N2 from the entry image P1 and the exit image P2 recorded in step S3. Based on the extraction result of the front license plate information N1 and the rear license plate information N2, the shape information F generated in step S1, and the charging information E generated in step S4, the determination unit 23 It is determined whether the vehicle that has passed is an unauthorized vehicle.

  In the fusion process of step S6, the fusion unit 24, for at least the vehicle determined to be an unauthorized vehicle in step S5, the shape information F generated in step S1, the entry image P1 and the exit image recorded in step S3. P2, the charging information E generated in step S4, and the front license plate information N1 and the rear license plate information N2 extracted in step S5 are collectively stored as travel history information in the database.

*** Explanation of effects ***
This embodiment has the following effects.

  In the present embodiment, since the approach image P1 and the exit image P2 of the vehicle passing through the automatic toll collection lane are recorded, it is possible to confirm the license plates on both the front and rear sides of the vehicle from the images. Therefore, according to the present embodiment, it is possible to monitor fraud of various types of vehicles. Specifically, it monitors for unauthorized vehicles 31 that replace only the front number plate that is easier to remove than the rear number plate with another one, and motorcycles 32 that have a number plate only at the rear. can do.

  In the toll road billing system, the driver's face and vehicle license plate information as evidence of unauthorized traffic were acquired in the conventional black and white image using a near infrared strobe, but in this embodiment, A lighting device 11 capable of obtaining sufficient illuminance even at night can be installed on the road, and the front and rear portions of the passing vehicle can be captured by the first camera 12 and the second camera 13 which are color cameras. Further, in the present embodiment, the first sensor 14 that is a laser sensor is used to perform shape determination at the same time as vehicle entry detection, so that captured images can be recorded corresponding to various cases of unauthorized traffic. As a result, there is a lot of information on the characteristics of the unauthorized traffic vehicle. Therefore, it becomes easy to search and identify malicious unauthorized passing vehicles from the database.

  In this embodiment, the vehicle shape and license plate information obtained from the vehicle-mounted device, the vehicle shape obtained from the laser sensor and the vehicle type determination result based on the shape, dimensional information such as vehicle height, vehicle width, vehicle length, etc., color The vehicle color obtained from the camera, the vehicle appearance photograph, the license plate information, the license plate image, etc., when wireless communication with the passing vehicle is not normally performed, and the passing vehicle is an unauthorized vehicle from the license plate information When determined, recording and creating a database makes it possible to easily search for and identify a malicious vehicle that performs fraudulent acts multiple times.

  FIG. 4 is a diagram illustrating an example of a hardware configuration of the control device 20.

  In FIG. 4, the control device 20 is a computer and includes hardware such as an output device 910, an input device 920, a storage device 930, and a processing device 940. The hardware is used by what is described as “unit” in the description of the embodiment of the present invention.

  The output device 910 is, for example, a display device such as an LCD (Liquid / Crystal / Display), a printer, or a communication module. The output device 910 is used for outputting or transmitting data, information, and signals by what is described as “unit” in the description of the embodiment of the present invention.

  The input device 920 is, for example, a keyboard, a mouse, a touch panel, and a communication module. The input device 920 is used for inputting or receiving data, information, and signals by what is described as a “unit” in the description of the embodiment of the present invention.

  The storage device 930 is, for example, a ROM (Read / Only / Memory), a RAM (Random / Access / Memory), a HDD (Hard / Disk / Drive), or an SSD (Solid / State / Drive). The storage device 930 stores a program 931 and a file 932. The program 931 includes a program for executing the processing described as “unit” in the description of the embodiment of the present invention. The file 932 includes data, information, signals, and the like that are calculated, processed, read, written, used, input, output, and the like by what is described as “unit” in the description of the embodiment of the present invention.

  The processing device 940 is, for example, a CPU (Central Processing Unit). The processing device 940 is connected to other hardware devices via a bus or the like, and controls those hardware devices. The processing device 940 reads the program 931 from the storage device 930 and executes the program 931. The processing device 940 is used for performing calculation, processing, reading, writing, use, input, output, and the like by what is described as “unit” in the description of the embodiment of the present invention.

  In the description of the embodiment of the present invention, what is described as “unit” may be replaced with “circuit”, “device”, and “apparatus”. Further, what is described as “part” in the description of the embodiment of the present invention may be “part” replaced with “process”, “procedure”, and “process”. That is, what is described as a “unit” in the description of the embodiment of the present invention is realized by software alone, hardware alone, or a combination of software and hardware. The software is stored in the storage device 930 as the program 931. The program 931 causes the computer to function as what is described as “unit” in the description of the embodiment of the present invention. Alternatively, the program 931 causes the computer to execute the processing described as “unit” in the description of the embodiment of the present invention.

  As mentioned above, although embodiment of this invention was described, you may implement this embodiment partially. For example, only one of those described as “parts” in the description of this embodiment may be adopted, or some arbitrary combinations may be adopted. In addition, this invention is not limited to this embodiment, A various change is possible as needed.

  DESCRIPTION OF SYMBOLS 10 Vehicle monitoring system, 11 Illumination device, 12 1st camera, 13 2nd camera, 14 1st sensor, 15 2nd sensor, 16 Radio | wireless part, 20 Control apparatus, 21 Detection part, 22 Recording part, 23 Determination unit, 24 fusion unit, 30 lanes, 31 automobile, 32 motorcycle, 910 output device, 920 input device, 930 storage device, 931 program, 932 file, 940 processing device.

Claims (5)

A first camera that captures an image of the direction of the entrance of the lane from a location closer to the exit than the entrance of the lane for automatic fee collection;
A second camera that captures an image of the direction of the exit of the lane from a location closer to the entrance than the exit of the lane;
A sensor for detecting a vehicle entering the lane and a vehicle exiting the lane;
An approach image, which is an image taken by the first camera when a vehicle entering the lane is detected by the sensor, and the second image when a vehicle exiting the lane is detected by the sensor. A vehicle monitoring system comprising: a recording unit that records an exit image that is an image captured by a camera. The information described in the vehicle license plate shown in the approach image recorded by the recording unit is extracted as front license plate information, and the vehicle license plate shown in the exit image recorded by the recording unit Is extracted as rear license plate information, and based on the extraction result of the front license plate information and the rear license plate information, it is determined whether the vehicle that has passed through the lane is an unauthorized vehicle. The vehicle monitoring system according to claim 1, further comprising a determination unit. The sensor further detects the shape of a vehicle passing through the lane,
The determination unit determines the type of the vehicle that has passed through the lane from the shape detected by the sensor, and in addition to the extraction result of the front license plate information and the rear license plate information, the determination result of the type The vehicle monitoring system according to claim 2, wherein it is determined whether the vehicle that has passed through the lane is an unauthorized vehicle based on the vehicle. A lighting device that emits white light from above the lane toward the road surface of the lane;
The first camera and the second camera take a color image using light emitted from the lighting device at least at night,
The vehicle monitoring system according to any one of claims 1 to 3, wherein the recording unit records the color image as the entry image and the exit image. The first camera takes an image of the direction of the entrance of the lane from a location closer to the exit than the entrance of the lane for automatic toll collection,
The second camera takes an image of the direction of the exit of the lane from a location closer to the entrance than the exit of the lane,
A sensor detects a vehicle entering the lane and a vehicle leaving the lane;
When the recording unit detects a vehicle entering the lane by the sensor, an approach image that is an image taken by the first camera, and a vehicle exiting the lane by the sensor A vehicle monitoring method for recording an exit image that is an image captured by the second camera.

Images