JP2007122355A - License plate reader and license plate read control method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve a recognition rate of license numbers even when a traffic condition changes. <P>SOLUTION: An image of a license plate of a vehicle is picked up obliquely from above ahead of the vehicle which is running or stops on the road, the picked up image is processed, license numbers of the license plate are recognized, and sparsity of vehicles or congestion of traffic condition is decided (S111, 122, 132, and 142). When it is decided to be sparse because the numbers are easily recognizable, a range of image pickup is controlled by changing a camera angle of declination to 15°; when the traffic is decided to be congested, the range of image pickup is controlled by changing the camera angle of declination to 30°, larger than 15° (S122 to 124, 132 to 134, and 142 to 144). A running position of the vehicle against a lane is decided (S112) and, by changing a rotation angle of the camera in accordance with the decided running position, the range of image pickup is controlled (S121, 123, 124, 131, 133, 134, 141, 143, and 144). <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a license plate reading device and a license plate reading control method, and more particularly to a license plate reading device suitable for reading a license plate and a license plate reading control method.

  Conventionally, a camera is installed on the upper part of the road in order to capture the vehicle number on the road. This camera captures the license plate image with the vertical resolution as high as possible to increase the number recognition rate, so that the camera imaging direction is as shallow as possible with respect to the license plate normal. Can be fixedly mounted on.

  However, when the vehicle is congested, there is a problem that the license plate to be imaged is hidden behind the front vehicle and the license plate cannot be imaged. In order to solve this problem, it is conceivable that the camera is fixed so that the imaging direction of the camera is deeper than the aforementioned shallow angle with respect to the normal of the license plate.

  However, when imaging is performed at such a deep angle, the captured license plate is captured as an image in which the longitudinal direction of the license plate is made shorter than when imaging is performed at a shallow angle. For this reason, when recognizing the number of the license plate, the resolution in the vertical direction of the license plate is lowered, resulting in a problem that the recognition rate of the number is lowered.

  In Patent Document 1, an image of a vehicle traveling on the road is acquired, and character recognition of a license plate in the acquired image is performed to recognize the vehicle number. A width direction position detecting means for detecting a traveling position in the road width direction and a means for changing the imaging area of the imaging means according to the output of the width direction position detecting means are provided, and the vehicle number based on the image captured by the imaging means Has been disclosed.

According to this vehicle number recognition system, the imaging area of the imaging means can be made to correspond to the traveling direction of the vehicle in the width direction, and the vehicle number image of the vehicle traveling on the wide road can be reliably acquired ( For example, paragraph 0005 of Patent Document 1).
JP 2002-42290 A

  When the license plate is imaged by the vehicle number recognition system disclosed in Patent Document 1, if the vehicle is congested, the license plate of the vehicle traveling in the lane near the camera on the wide road is imaged. be able to. However, the problem is that the license plate of a vehicle traveling in a lane that is not close to the camera is behind the vehicle that travels in the lane close to the camera almost continuously in a traffic jam, making it impossible to capture the license plate. was there.

  The present invention has been made to solve the above-described problems, and one of the objects of the present invention is to provide a license plate reading apparatus and a license plate reading control method capable of improving the number recognition rate. Is to provide.

  In order to solve the above-described problem, according to an aspect of the present invention, a license plate reader includes a camera, a number recognition unit, a traffic situation determination unit, and a camera control unit.

  The camera images the number plate of the vehicle from an obliquely upper part at the front or rear of the vehicle running or stopped on the road. The number recognizing unit processes the image captured by the camera and recognizes the number on the license plate. The traffic situation determination unit determines the traffic situation of the vehicle. The camera control unit controls the imaging range of the camera according to the traffic situation determined by the traffic condition determination unit.

  According to the present invention, the license plate reading device captures the license plate of the vehicle from the diagonally upper part of the front or rear of the vehicle running or stopped on the road, and the captured image is processed to obtain the license plate. The number is recognized. Further, the traffic situation of the vehicle is determined, and the imaging range of the camera is controlled according to the determined traffic condition.

  For this reason, since the number plate image of the imaging range controlled according to the determined traffic situation is taken, a license plate image that is easier to recognize can be obtained as compared with the case where it is not according to the traffic situation. . As a result, it is possible to provide a license plate reader capable of improving the number recognition rate even when the traffic situation changes.

  Preferably, the camera control unit controls the imaging range so that the number is easily recognized by the number recognition unit.

  According to the present invention, the imaging range is controlled by the license plate reader so that the number is easily recognized. For this reason, since the license plate image in the imaging range controlled so that the number is easily recognized is picked up, a license plate image that is easy to recognize can be obtained. As a result, the number recognition rate can be further improved.

Preferably, the traffic situation determination unit determines the degree of congestion of the vehicle as the traffic situation.
According to this invention, the image of the number plate in the imaging range controlled so that the number is easily recognized according to the determined degree of traffic jam of the vehicle is captured. For this reason, it is possible to obtain a license plate image that is easier to recognize than in the case where the degree of congestion is not met. As a result, even if the degree of congestion changes, the number recognition rate can be improved.

Preferably, the traffic condition determination unit determines whether the vehicle is congested or light as the traffic condition.
According to the present invention, the image of the license plate in the imaging range controlled so that the number is easily recognized according to the determined traffic jam or quietness of the vehicle is captured. For this reason, it is possible to obtain a license plate image that is easier to recognize than in the case of not responding to traffic jams or light traffic. As a result, the recognition rate of the number can be improved even when the traffic jam or the change of the vehicle changes.

  Preferably, the license plate reader further includes a passing number detecting unit that detects the number of passing vehicles within a predetermined time, and the traffic condition determining unit determines a traffic condition according to the number of passing vehicles within the predetermined time. .

  According to this invention, the image of the license plate in the imaging range controlled so that the number is easily recognized according to the traffic situation determined according to the number of vehicles passing within the predetermined time is taken. There is a correlation between the number of vehicles passing within a predetermined time. For this reason, since the image of the license plate in the imaging range controlled so that the number is easily recognized according to the distance between the vehicles is captured, the image of the license plate that is easier to recognize than when not corresponding to the distance between the vehicles. can get. As a result, even if the distance between the vehicles changes, the number recognition rate can be improved.

  Preferably, the traffic situation determination unit determines an traffic situation by processing an image captured by the camera.

  According to the present invention, the image of the license plate in the imaging range controlled so that the number is easily recognized according to the traffic situation determined by processing the image captured by the camera is captured. For this reason, even if it does not provide the other detection part which detects a traffic condition, a traffic condition can be discriminate | determined with the camera which is the structure contained in a license plate reader. As a result, the cost for determining the traffic situation can be suppressed.

  Preferably, the license plate reading device further includes a traffic information receiving unit that receives traffic information from the outside, and the traffic condition determining unit determines the traffic condition based on the traffic information received by the traffic condition receiving unit.

  According to this invention, the image of the license plate in the imaging range controlled so that the number is easily recognized according to the traffic situation determined based on the traffic information received from the outside is captured. For this reason, even if it does not provide the detection part which detects a traffic condition, only by enabling it to receive traffic information from the outside, a traffic condition can be discriminate | determined based on the traffic information from the outside. As a result, it is possible to reduce the cost of providing a detection unit for detecting traffic conditions.

  Preferably, the camera control unit controls the imaging range by changing the depression angle of the camera so that the recognition rate of the number recognized by the number recognition unit is increased according to the traffic situation determined by the traffic condition determination unit. To do.

  According to the present invention, the number plate of the imaging range controlled so that the number is easily recognized by changing the depression angle of the camera so that the recognition rate of the recognized number is increased according to the determined traffic situation. Images are captured. For this reason, it is possible to obtain a license plate image that is easier to recognize than when the depression angle is not changed according to traffic conditions. As a result, even if the traffic situation changes, the number recognition rate can be improved by changing the depression angle of the camera accordingly.

  Preferably, the camera control unit controls the imaging range by changing the depression angle of the camera to be deeper as the degree of congestion determined by the traffic situation determination unit increases.

  According to the present invention, the number plate image in the imaging range controlled so that the number is easily recognized is captured by changing the depression angle of the camera as the determined degree of traffic congestion increases. The For this reason, it is possible to obtain a license plate image that is easier to recognize than when the depression angle of the camera is not changed according to the degree of traffic jam. As a result, even if the degree of congestion changes, the number recognition rate can be improved by changing the depression angle of the camera accordingly.

  Preferably, the camera control unit controls the imaging range by changing the depression angle of the camera in stages.

  According to the present invention, the depression angle of the camera is changed stepwise according to the degree of traffic jam. For this reason, it is possible to control the depression angle of the camera in accordance with the degree of traffic congestion by a simple method compared to the case where the depression angle of the camera is continuously changed. As a result, the number recognition rate can be improved more easily.

  Preferably, the camera control unit controls the imaging range by changing the depression angle of the camera to the first predetermined angle when the traffic condition is determined to be quiet by the traffic condition determination unit, and the traffic condition determination unit When it is determined that the traffic situation is traffic jam, the imaging range is controlled by changing the depression angle of the camera to a second predetermined angle deeper than the first predetermined angle.

  According to the present invention, when the determined traffic situation is quiet, the depression angle of the camera is changed to the first predetermined angle, and when it is congested, the depression angle of the camera is deeper than the first predetermined angle. The number plate image in the imaging range controlled so that the number is easily recognized by being changed to is captured. For this reason, it is possible to obtain a license plate image that is easier to recognize than in the case where the depression angle of the camera is not changed according to traffic jam or light. As a result, even if the traffic situation changes due to traffic jam or light traffic, the number recognition rate can be improved by changing the depression angle of the camera accordingly.

  Preferably, the vehicle control device further includes a travel position determination unit that determines a travel position of the vehicle with respect to the lane, and the camera control unit changes the rotation angle of the camera according to the travel position of the vehicle determined by the travel position determination unit. Control the imaging range.

  According to the present invention, by controlling the rotation angle of the camera in accordance with the determined traveling position of the vehicle, the imaging is controlled so that a large number of license plates can be imaged and the numbers are easily recognized. An image of the range license plate is taken. For this reason, as compared with the case where the rotation angle is not changed according to the traveling position, it is possible to image more license plates and obtain a license plate image that is easier to recognize. As a result, even if the traveling position changes due to a parked vehicle, construction work, snow accumulation, or the like, the number recognition rate can be improved by changing the rotation angle of the camera accordingly.

  Preferably, the camera control unit controls the imaging range by changing the rotation angle of the camera stepwise.

  According to the present invention, the rotation angle of the camera is changed stepwise according to the travel position. For this reason, compared with the case where the rotation angle of a camera is changed continuously, the rotation angle of a camera can be controlled according to a running position by a simple method. As a result, the number recognition rate can be improved more easily.

  According to another aspect of the present invention, a license plate reading control method is a method for controlling a camera that images a vehicle's license plate from an obliquely upper part at the front or rear of a vehicle running or stopped on a road. Processing the image captured by the camera to recognize the number on the license plate; determining the traffic condition of the vehicle; and controlling the imaging range of the camera according to the determined traffic condition; including.

  According to the present invention, since the license plate image of the imaging range controlled according to the determined traffic situation is taken, the license plate image that is easier to recognize than the case where it is not in accordance with the traffic situation. Is obtained. As a result, it is possible to provide a license plate reading control method capable of improving the number recognition rate even when the traffic situation changes.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that the same or corresponding parts in the drawings are denoted by the same reference numerals and description thereof will not be repeated.

  FIG. 1 is a sketch of a license plate reader 10 according to an embodiment of the present invention.

  Referring to FIG. 1, a license plate reader 10 is a device that captures a license plate of a vehicle, recognizes the number of the license plate by performing image processing on the captured image. The license plate reader 10 includes a camera unit 1 and a control unit 2.

  The camera unit 1 is installed above each lane of the roadway so as not to contact the vehicle. The camera unit 1 picks up an image of a vehicle license plate from an oblique upper part in front of a vehicle running or stopped on a road.

  Note that the camera unit 1 may take an image of the vehicle license plate from an oblique upper part behind the vehicle. Further, one camera unit 1 may be installed for each of a plurality of lanes, for example, two lanes. In FIG. 1, the camera unit 1 is installed near the intersection. However, the present invention is not limited to this, and the camera unit 1 may be installed on an upper portion of the road other than the vicinity of the intersection.

  The control unit 2 is installed around a sidewalk near the camera unit 1. The control unit 2 controls the camera unit 1.

  FIG. 2 is a control block diagram of the license plate reader according to the embodiment of the present invention.

  Referring to FIG. 2, camera unit 1 includes a camera 11 and a camera driving unit 12. The camera 11 is controlled by the control unit 2 and has a zoom function for enlarging or reducing the imaging area. The camera 11 outputs an image signal indicating the captured image to the control unit 2. The camera driving unit 12 is controlled by the control unit 2 to drive the camera 11 so as to change the depression angle and the rotation angle of the camera 11.

  The vehicle detector 3 is installed immediately above the road, emits ultrasonic waves from the head toward the ground, and measures the time until the ultrasonic waves are reflected back to the road or vehicle, thereby determining the presence or absence of the vehicle. Sense. Each vehicle sensor 3 transmits the sensed sensing information to the control unit 2.

  The vehicle detector 3 is a presence type vehicle detector that can detect the presence of a vehicle even when the vehicle is stopped in such a detection region, or a case where the vehicle is stopped even in the detection region. There is a vehicle type detector that can detect a passing type that cannot be detected, and an image type that senses a vehicle in multiple lanes by processing images taken by a camera.

  The control unit 2 includes an A / D converter 24, an image processing circuit 23, a control unit 20, and a communication unit 25. The A / D converter 24 converts an image signal that is an analog signal from the camera 11 into image data that is digital data, and sends the image data to an image processing circuit.

  The image processing circuit 23 performs image processing on the image data received from the A / D converter 24 and generates image preprocessing data for recognizing the license plate. As the image processing circuit, for example, the circuit shown in FIG. 3 of Japanese Patent Laid-Open No. 3-265985 (hereinafter referred to as “known document”) can be used.

  The control unit 20 includes a CPU (Central Processing Unit) 21 that executes a program, and a memory 22 that stores a program to be executed, data being executed, and data of a program execution result.

  The control unit 20 performs number recognition processing for recognizing the number of the license plate based on the image preprocessing data received from the image processing circuit 23. As this number recognition process, for example, the process shown in FIG. The control unit 20 controls the communication unit 25 so as to transmit number information indicating the recognized number to the traffic control center 4.

  Further, the control unit 20 performs a camera control process for controlling the imaging region of the camera 11 based on the image preprocessing data received from the image processing circuit 23 and the sensing information received from the vehicle detector 3. The camera control process will be described later with reference to FIG.

  The communication unit 25 is controlled by the control unit 20 and transmits the number information received from the control unit 20 to the traffic control center 4. The traffic control center 4 stores the number information received from the control unit 2 in a database in association with identification data for identifying the control unit 2. Thereby, the traffic control center 4 can grasp the number of the vehicle that has passed the point where the control unit 2 indicated by the identification data is installed.

  FIG. 3 is a flowchart showing the flow of the camera control process executed by the license plate reader 10 according to the embodiment of the present invention.

  Referring to FIG. 3, first, in step S111, control unit 20 determines a point where vehicle detector 3 is installed based on the detection information received from vehicle detector 3 for a predetermined time (for example, 10 minutes). The average value of the number of vehicles passing, which is the number of vehicles that have passed through, is calculated.

  Specifically, the control unit 20 counts the number of vehicles passing by a counter every time sensing information from the vehicle detector 3 is received, and at every unit time (for example, 1 minute) shorter than a predetermined time, The count value is stored in the memory 22 and the counter is reset. Then, when calculating the average value of the number of vehicles passing through the vehicle, the count value within a predetermined time is read from the memory 22, added to each other, and divided by the predetermined time, thereby calculating the average value of the number of vehicles passing through the predetermined time. be able to.

  Next, in step S <b> 112, the control unit 20 calculates an average value of the traveling position of the vehicle with respect to the lane based on the image preprocessing data received from the image processing circuit 23.

  Specifically, the control unit 20 processes the image preprocessing data, and sequentially stores the position data obtained by quantifying the lateral position with reference to the center of the lane in the image of the license plate for each vehicle in the memory 22. By storing the position data within a predetermined time from the memory 22, adding each, and dividing by the number of objects to be added, the average value of the vehicle travel position within the predetermined time is obtained. Can be calculated.

  In step S121, the control unit 20 determines whether or not the average value of the vehicle travel positions calculated in step S112 is in the middle range of the lane. For example, the control unit 20 determines that the average value of the vehicle travel position is the center range of the lane when the lane is divided into three equal parts and the average value of the vehicle travel position is included in the middle range. .

  When it is determined that the average value of the vehicle traveling position is in the middle range of the lane (YES in step S121), in step S122, the control unit 20 is based on the average value of the number of passing vehicles calculated in step S111. Determine whether the vehicle traffic is congested or quiet. Specifically, the control unit 20 determines that there is a traffic jam when the average value of the number of vehicles passing is greater than or equal to a predetermined number, and determines that it is quiet when the average value is less than the predetermined number.

  When it is determined that it is quiet (when it is quiet in step S122), the control unit 20 controls the camera 11 and the camera driving unit 12 so as to capture the imaging region A in step S123. After that, the control unit 20 returns the process to be executed to the calling process of the camera control process.

FIG. 4 is a diagram showing an imaging area of the camera unit 1 according to the embodiment of the present invention.
Referring to FIG. 4, in the present embodiment, an imaging area from imaging area A to imaging area F is determined in advance as an area to be imaged by camera unit 1. The imaging area A to the imaging area C are areas that are imaged at a shallow depression angle (15 ° in the present embodiment). The imaging area D to the imaging area F are areas that are imaged at a deep depression angle (30 ° in the present embodiment) as compared with the imaging area A to the imaging area C.

  In addition, the imaging area A and the imaging area D are suitable for imaging a vehicle traveling in the center range of the lane. The imaging area C and the imaging area E are suitable for imaging a vehicle traveling on the right side of the lane. The imaging area B and the imaging area F are suitable for imaging a vehicle traveling to the left of the lane.

  Returning to FIG. 3, when it is determined that there is a traffic jam (in the case of a traffic jam in step S <b> 122), the control unit 20 controls the camera 11 and the camera drive unit 12 so as to capture the imaging region D in step S <b> 124. After that, the control unit 20 returns the process to be executed to the calling process of the camera control process.

  When it is determined that the average value of the vehicle travel position is not in the middle range of the lane (NO in step S121), in step S131, the control unit 20 determines that the average value of the vehicle travel position calculated in step S112 is closer to the right side of the lane. It is determined whether or not. For example, when the average value of the vehicle travel position is included in the range on the right side in the traveling direction of the range obtained by dividing the lane horizontally into three equal parts, the control unit 20 has a range in which the average value of the vehicle travel position is on the right side of the lane. It is judged that.

  When it is determined that the average value of the vehicle travel position is in the right side of the lane (in the case of YES in step S131), in step S132, the control unit 20 is based on the average value of the number of passing vehicles calculated in step S111. Determine whether the vehicle traffic is congested or quiet.

  When it is determined that it is quiet (when it is quiet in step S132), the control unit 20 controls the camera 11 and the camera driving unit 12 so as to capture the imaging region C in step S133. After that, the control unit 20 returns the process to be executed to the calling process of the camera control process.

  When it is determined that there is a traffic jam (in the case of traffic jam in step S132), the control unit 20 controls the camera 11 and the camera drive unit 12 so as to capture the imaging area E in step S134. After that, the control unit 20 returns the process to be executed to the calling process of the camera control process.

  If it is determined that the average value of the vehicle travel position is not in the range to the right of the lane (in the case of NO in step S131), in step S141, the control unit 20 determines that the average value of the vehicle travel position calculated in step S112 is to the left of the lane. It is determined whether or not. For example, when the average value of the vehicle travel position is included in the left-side range in the traveling direction of the range obtained by dividing the lane horizontally into three equal parts, the control unit 20 has a range in which the average value of the vehicle travel position is closer to the left side of the lane. It is judged that.

  When it is determined that the average value of the vehicle traveling position is in the range to the left of the lane (in the case of YES in step S141), in step S142, the control unit 20 is based on the average value of the number of passing vehicles calculated in step S111. Determine whether the vehicle traffic is congested or quiet.

  When it is determined that it is quiet (when it is quiet in step S142), in step S143, the control unit 20 controls the camera 11 and the camera driving unit 12 so as to capture the imaging region B. After that, the control unit 20 returns the process to be executed to the calling process of the camera control process.

  If it is determined that there is a traffic jam (in the case of traffic jam in step S142), the control unit 20 controls the camera 11 and the camera drive unit 12 so as to capture the imaging region F in step S144. After that, the control unit 20 returns the process to be executed to the calling process of the camera control process.

  When it is determined that the average value of the vehicle travel position is not in the left-hand lane range (NO in step S141), the control unit 20 returns the process to be executed to the caller process of this camera control process.

  FIG. 5 is a diagram showing the relationship between the depression angle of the camera 11 and the distance between vehicles in the embodiment of the present invention.

  Referring to FIG. 5, when the distance between vehicles is equal to or greater than b, the camera unit 1 can capture the number even if the depression angle of the camera 11 is 15 °. In addition, if the front vehicle of the two vehicles is not a vehicle with a low rear vehicle height such as a sedan type, but a vehicle with a high rear vehicle height such as a wagon type or a truck, the distance between vehicles that can be imaged at a depression angle of 15 ° Becomes narrower than b.

  When the depression angle of the camera 11 is 30 °, the number can be captured by the camera unit 1 if the distance between the vehicles is a or more.

  In addition, the predetermined number with respect to the vehicle passing number described in step S122 in FIG. 3 is determined in advance based on b which is the distance between the vehicles. That is, if the distance between vehicles is equal to or greater than b, the predetermined number is determined such that the number of vehicles passing in a predetermined time is equal to or greater than the predetermined number.

  FIG. 6 is a diagram illustrating an image captured by the camera 11 when the distance between the vehicles becomes narrow when the depression angle of the camera 11 is shallow in the embodiment of the present invention.

  Referring to FIG. 6, when the depression angle of camera 11 is shallow (for example, in the case of 15 ° described above) as in the case of imaging from imaging area A to imaging area C described in FIG. 4, the distance between the vehicles is narrow. When it becomes (for example, when it becomes less than b mentioned above), the license plate of the rear vehicle is hidden behind the front vehicle. For this reason, the license plate of the rear vehicle cannot be imaged by the camera unit 1.

  FIG. 7 is a diagram showing an image captured by the camera 11 when the depression angle of the camera 11 is increased when the distance between the vehicles is narrow in the embodiment of the present invention.

  Referring to FIG. 7, even when the distance between vehicles is narrow (for example, when the distance is less than b described above), when imaging from imaging region D to imaging region F described in FIG. 4 is performed. By making the depression angle of the camera 11 deeper (for example, by setting it to 30 ° as described above), the number plate of the rear vehicle is not hidden behind the front vehicle. For this reason, the license plate of the rear vehicle can be imaged by the camera unit 1.

  FIG. 8 is a diagram showing a case where the vehicle travel position deviates from the center range of the lane in the embodiment of the present invention.

  Referring to FIG. 8, since there is a parked vehicle at the left end of the road, the traveling position of the vehicle is shifted to the right side in the traveling direction of the vehicle. Even in such a case, the license plate often attached to the center of the vehicle is imaged by changing the rotation angle of the camera 11 so as to image the imaging area C or the imaging area E described in FIG. An image can be taken not in the vicinity of the end of the area but in the middle of the imaging area. For this reason, it becomes possible to image even a license plate attached to the right end of the vehicle.

  As described above, according to the license plate reader 10 in the present embodiment, as described in FIG. 1, the license plate of the vehicle is imaged from the diagonally upper part in front of the vehicle running or stopped on the road. Is done. In addition, as described with reference to FIG. 2, the captured image is processed to recognize the license plate number.

  Further, as described in step S111, step S122, step S132, and step S142 in FIG. 3, the traffic situation of the vehicle is determined. Further, as described in step S123, step S124, step S133, step S134, step S143, step 144, and FIG. 4, the imaging range of the camera 11 is controlled according to the determined traffic situation.

  In this way, the license plate reading device 10 picks up an image of the license plate in the imaging range controlled according to the determined traffic situation, so that the license plate reader 10 recognizes more than the case where it is not in accordance with the traffic situation. An easy license plate image is obtained. As a result, even if the traffic situation changes, the number recognition rate can be improved.

  Further, according to the license plate reading device 10, as described in step S123, step S124, step S133, step S134, step S143, step 144, and FIG. 4, the imaging range is controlled so that the number is easily recognized. Is done.

  Thus, the imaging range is controlled by the license plate reader 10 so that the number is easily recognized. For this reason, since the license plate image in the imaging range controlled so that the number is easily recognized is picked up, a license plate image that is easy to recognize can be obtained. As a result, the number recognition rate can be further improved.

  Further, according to the license plate reading device 10, as described in Step S122, Step S132, and Step S142 in FIG. 3, the degree of traffic congestion of the vehicle in two stages of traffic jam or light traffic is determined as the traffic situation.

  In this way, the license plate reading device 10 captures an image of the license plate in the imaging range that is controlled so that the number is easily recognized according to the determined degree of traffic congestion of the vehicle. Compared to the case, it is possible to obtain a license plate image that is easier to recognize. As a result, even if the degree of congestion changes, the number recognition rate can be improved.

  In addition, according to the license plate reader 10, as described in step S111 in FIG. 3, the number of vehicles passing within a predetermined time is detected. Further, as described in step S122, step S132, and step S142 in FIG. 3, the traffic situation is determined according to the detected number of passing vehicles.

  In this way, the license plate reader 10 captures an image of the license plate in the imaging range controlled so that the number is easily recognized according to the traffic situation determined according to the number of vehicles passing within a predetermined time. The Further, there is a correlation between the number of vehicles passing within a predetermined time and the number of vehicles. For this reason, since the image of the license plate in the imaging range controlled so that the number is easily recognized according to the distance between the vehicles is captured, the image of the license plate that is easier to recognize than when not corresponding to the distance between the vehicles. can get. As a result, even if the distance between the vehicles changes, the number recognition rate can be improved.

  Further, the license plate reader 10 determines the number according to the determined traffic situation as described in FIG. 3 from step S122 to step S124, step S132 to step S134, step S142 to step S144, and FIG. The imaging range is controlled by changing the depression angle of the camera 11 so that the recognition rate increases.

  In this way, the license plate reader 10 controls the angle of the camera 11 so that the recognition rate of the recognized number is increased in accordance with the determined traffic situation so that the number is easily recognized. An image of the license plate in the imaged range is captured. For this reason, it is possible to obtain a license plate image that is easier to recognize than when the depression angle is not changed according to traffic conditions. As a result, even if the traffic situation changes, the recognition rate of the number can be improved by changing the depression angle of the camera 11 accordingly.

  Further, according to the license plate reader 10, from step S122 to step S124 in FIG. 3, from step S132 to step S134, from step S142 to step S143, and as described with reference to FIG. As the angle increases, the angle of depression of the camera is changed to be deeper, whereby the imaging range is controlled.

  As described above, the depression angle of the camera 11 is changed so that the depression angle of the camera 11 becomes deeper as the degree of congestion of the determined vehicle increases, so that an image of the number plate in the imaging range controlled so that the number is easily recognized is captured. The For this reason, compared with the case where the depression angle of the camera 11 is not changed according to the degree of traffic congestion, a license plate image that is easier to recognize can be obtained. As a result, even if the degree of congestion changes, the recognition angle of the number can be improved by changing the depression angle of the camera 11 accordingly.

  In addition, according to the license plate reading device 10, as described with reference to FIG. 5, the depression angle of the camera 11 is changed stepwise between a shallow depression angle of 15 ° and a deep depression angle of 30 °, whereby an imaging range is obtained. Is controlled.

  In this way, the depression angle of the camera 11 is changed stepwise by the license plate reader 10 according to the degree of congestion. For this reason, compared with the case where the depression angle of the camera 11 is continuously changed, the depression angle of the camera 11 can be controlled more easily according to the degree of traffic congestion. As a result, the number recognition rate can be improved more easily.

  Further, according to the license plate reader 10, as described in steps S122 to S124, steps S132 to S134, and steps S142 to S144 in FIG. In this case, when the depression angle of the camera 11 is changed to 15 °, the imaging range is controlled, and when it is determined that the traffic situation is a traffic jam, the depression angle of the camera 11 is changed to 30 ° deeper than 15 °. As a result, the imaging range is controlled.

  As described above, the depression angle of the camera 11 is changed to 15 ° by the license plate reading device 10 when the determined traffic situation is quiet, and the depression angle of the camera is changed to 30 ° deeper than 15 ° when there is a traffic jam. Thus, an image of the license plate in the imaging range controlled so that the number is easily recognized is captured. For this reason, it is possible to obtain a license plate image that is easier to recognize than in the case where the depression angle of the camera 11 is not changed according to traffic jam or light. As a result, even if the traffic situation changes to traffic jam or quiet, the depression angle of the camera 11 is changed accordingly, so that the number recognition rate can be improved.

  Further, according to the license plate reader 10, as described in step S112 in FIG. 3, the traveling position of the vehicle with respect to the lane is determined. Further, as described with reference to step S121, step S123, step S124, step S131, step S133, step S134, step S141, step S143, step S144, FIG. 4, and FIG. The imaging range is controlled by changing the rotation angle of the camera 11 according to the travel position.

  As described above, the license plate reader 10 changes the rotation angle of the camera 11 according to the determined traveling position of the vehicle, so that many license plates can be imaged and the number is recognized. An image of the license plate in the imaging range controlled so as to be easy is taken. For this reason, compared with the case where a rotation angle is not changed according to a driving | running | working position, more license plates can be imaged and the image of a license plate which is easier to recognize is obtained. As a result, even when the traveling position changes due to a parked vehicle, construction work, snow accumulation, or the like, the number recognition rate can be improved by changing the rotation angle of the camera 11 accordingly.

  Further, according to the license plate reading device 10, the rotation angle of the camera 11 is stepwise as described in step S123, step S124, step S133, step S134, step S143, step S144, and FIG. Is changed, the imaging range is controlled.

  As described above, the license plate reader 10 changes the rotation angle of the camera 11 in a stepwise manner in accordance with the travel position. For this reason, compared with the case where the rotation angle of the camera 11 is continuously changed, the rotation angle of the camera 11 can be controlled more easily according to the travel position. As a result, the number recognition rate can be improved more easily.

  In the present embodiment, the invention has been described as the license plate reader 10. However, the present invention is not limited to this, and the invention can be understood as a license plate reading control method or a license plate reading control program in which the control unit 20 of the control unit 2 of the license plate reading apparatus 10 executes the camera control process described in FIG. it can.

  Further, in the present embodiment, the number of passing vehicles within a predetermined time is calculated based on the sensing information from the vehicle detector 3, and traffic congestion or lightness is determined based on the number of passing vehicles. However, the present invention is not limited to this, and an image captured by the camera 11 may be processed to determine whether there is a traffic jam or a quiet passage.

  In this way, the image of the license plate in the imaging range controlled so that the number is easily recognized according to the traffic situation determined by processing the image captured by the camera 11 is captured. For this reason, even if the vehicle detector 3 for detecting the traffic situation is not provided, the traffic situation can be determined by the camera 11 that is included in the license plate reader 10. As a result, the cost for determining the traffic situation can be suppressed.

  Further, it may be determined whether there is traffic jam or light traffic based on traffic information received from the traffic control center 4 via the communication unit 25.

  In this way, an image of the license plate in the imaging range controlled so that the number is easily recognized according to the traffic situation determined based on the traffic information received from the traffic control center 4 is captured. For this reason, even if the vehicle detector 3 for detecting the traffic situation is not provided, it is based on the traffic information from the traffic control center 4 only by providing the communication unit 25 capable of receiving the traffic information from the traffic control center 4. To determine the traffic situation. As a result, it is possible to reduce the cost of providing the vehicle detector 3 for detecting the traffic situation.

  Further, the camera 11 may be a camera that captures a moving image or a camera that continuously captures still images.

  In addition, the traffic situation is divided into two stages of traffic jam or quiet, and the depression angle of the camera 11 is changed in two stages so that the number can be easily recognized according to the traffic situation. To control. However, the present invention is not limited to this, and the traffic situation may be determined by dividing into two or more levels of traffic congestion. Further, the depression angle of the camera 11 may be continuously switched according to the degree of traffic jam.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

It is a sketch of the license plate reading apparatus in embodiment of this invention. It is a control block diagram of the license plate reader in the embodiment of the present invention. It is a flowchart which shows the flow of the camera control process performed by the license plate reader in embodiment of this invention. It is a figure which shows the imaging area of the camera unit in embodiment of this invention. It is a figure which shows the relationship between the depression angle of the camera in this Embodiment, and the distance between vehicles. It is a figure which shows the image imaged with the camera when the head angle of a vehicle becomes narrow when the depression angle of a camera is shallow in embodiment of this invention. It is a figure which shows the image imaged with the camera when the depression angle of a camera is made deep when embodiment of this invention the space between vehicles is narrow. It is a figure which shows the case where a vehicle travel position deviates from the center range of a lane in embodiment of this invention.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 Camera unit, 2 Control unit, 3 Vehicle detector, 4 Traffic control center, 10 License plate reader, 11 Camera, 12 Camera drive part, 20 Control part, 21 CPU, 22 Memory, 23 Image processing circuit, 24 A / D converter, 25 communication section.

Claims (14)

A camera that images the license plate of the vehicle from an oblique upper part of the front or rear of the vehicle running or stopped on the road;
Number recognition means for processing an image captured by the camera and recognizing the number of the license plate;
A traffic condition determining means for determining the traffic condition of the vehicle;
A license plate reading apparatus comprising: camera control means for controlling an imaging range of the camera according to the traffic situation determined by the traffic condition determination means.   The license plate reading device according to claim 1, wherein the camera control unit controls the imaging range so that the number is easily recognized by the number recognition unit.   The license plate reader according to claim 1, wherein the traffic situation determination unit determines a degree of traffic jam of the vehicle as the traffic situation.   The license plate reader according to claim 1, wherein the traffic condition determination unit determines whether the traffic condition is a traffic jam or a light traffic. Further comprising a passing number detecting means for detecting the number of passing vehicles within a predetermined time,
5. The license plate reader according to claim 1, wherein the traffic condition determination unit determines the traffic condition according to the number of passing vehicles detected by the passing number detection unit.   The license plate reader according to any one of claims 1 to 4, wherein the traffic situation determination unit processes an image captured by the camera to determine the traffic situation. A traffic information receiving means for receiving the traffic information from outside;
The license plate reader according to any one of claims 1 to 4, wherein the traffic situation determination unit determines the traffic situation based on traffic information received by the traffic condition reception unit.   The camera control means changes the depression angle of the camera so as to increase the recognition rate of the number recognized by the number recognition means according to the traffic situation determined by the traffic condition determination means, The license plate reader according to any one of claims 1 to 4, which controls an imaging range.   4. The number according to claim 3, wherein the camera control unit controls the imaging range by changing the depression angle of the camera to be deeper as the degree of congestion determined by the traffic situation determination unit increases. Plate reader.   The license plate reading apparatus according to claim 8 or 9, wherein the camera control unit controls the imaging range by changing a depression angle of the camera in a stepwise manner.   The camera control means controls the imaging range by changing the depression angle of the camera to a first predetermined angle when the traffic situation judgment means judges that the traffic situation is quiet by the traffic situation judgment means, The imaging range is controlled by changing a depression angle of the camera to a second predetermined angle that is deeper than the first predetermined angle when the traffic situation is determined to be a traffic jam by a situation determination unit. Item 5. A license plate reader according to Item 4. The vehicle further comprises travel position determination means for determining the travel position of the vehicle with respect to the lane,
The camera control unit controls the imaging range by changing a rotation angle of the camera in accordance with a vehicle travel position determined by the travel position determination unit. The license plate reader according to any one of the above.   The license plate reader according to claim 12, wherein the camera control unit controls the imaging range by changing a rotation angle of the camera in a stepwise manner. A license plate reading control method for controlling a camera that images a license plate of the vehicle from an oblique upper part of the front or rear of a vehicle running or stopped on a road,
Processing the image captured by the camera to recognize the number of the license plate;
Determining the traffic situation of the vehicle;
A license plate reading control method, comprising: controlling an imaging range of the camera according to the determined traffic situation.

Images