KR102608447B1 - System for Vehicle Number Recognition Control Using Artificial Intelligence and Method thereof - Google Patents

Abstract

The present invention relates to a vehicle number recognition control system and method using artificial intelligence.
According to the present invention, the license plate recognition control system includes a posture information acquisition unit that acquires basic posture information for cameras and IR lights installed in a plurality of license plate recognition devices, and a front image of a vehicle entering from the license plate recognition device. an image receiving unit, a license plate recognition unit that detects a license plate area by preprocessing the received front image, and obtains shape information of the license plate from the detected license plate area, and basic attitude information about the camera and IR lighting and the license plate It includes a control unit that inputs shape information into a previously learned learning model to obtain corrected posture information for a camera or IR lighting, and transmits the corrected posture information to a license plate recognition device.
According to the present invention, the posture of the camera or IR light can be corrected in real time according to the shape information of the license plate recognized using artificial intelligence, and can be controlled in real time according to the environment of each parking lot, thereby increasing the recognition rate of the license plate. You can. In addition, according to the present invention, it is possible to correct the posture of the camera and IR lighting without having to deploy professional manpower on site, which is effective in reducing labor costs.

Description

System for Vehicle Number Recognition Control Using Artificial Intelligence and Method thereof}

The present invention relates to a vehicle number recognition control system and method using artificial intelligence. More specifically, the present invention relates to a vehicle number recognition control system and method using artificial intelligence, by remotely controlling the posture of the camera and IR lighting included in the vehicle number recognition device using artificial intelligence, This relates to a license plate recognition control system and method for increasing the recognition rate of license plates of vehicles leaving the vehicle.

License plate recognition cameras, which were mainly used to crack down on speeding and violations, are being expanded to include intelligent parking control, including parking lot charging.

In general, the vehicle license plate recognition process proceeds in the following order: photographing a vehicle entering the entrance or exit of a parking lot using a license plate recognition camera, extracting the license plate from the captured image, and then printing the vehicle number.

Meanwhile, the camera installed in the license plate recognition device films the entering vehicle in a fixed state. The manager then checked the captured video and, if it was determined that the recognition rate for the vehicle's license plate was low, visited the site and corrected the camera's posture.

However, in order to correct the camera's posture through an on-site visit, professional personnel must be used, and due to the recently increased demand for parking lots, there was a problem of requiring a large number of personnel.

In addition, in the process of recognizing a vehicle's license plate, problems such as recognition errors in the vehicle's license plate occur due to environmental factors such as backlight, total reflection, and shadows from surrounding objects, and these recognition errors cause a decrease in the recognition rate of the vehicle's license plate. It's causing problems.

Therefore, there is a need to develop technology that can improve recognition speed and function by minimizing recognition errors of vehicle license plates by reducing environmental factors according to field conditions.

The technology behind the present invention is disclosed in Korean Patent Publication No. 10-2021-016960 (published on February 17, 2021).

According to the present invention, a vehicle number recognition control system and a vehicle number recognition control system for increasing the recognition rate of the license plate of an entering or exiting vehicle by remotely controlling the posture of the camera and IR lighting included in the vehicle number recognition device using artificial intelligence, and The purpose is to provide that method.

According to an embodiment of the present invention to achieve this technical problem, in a vehicle number recognition control system using artificial intelligence, an attitude information acquisition unit that acquires basic attitude information about cameras and IR lights installed in a plurality of vehicle number recognition devices; An image receiver that receives a front image of an approaching vehicle from the license plate recognition device, a license plate recognition unit that pre-processes the received front image to detect a license plate area and obtains shape information of the license plate from the detected license plate area; Then, input the basic posture information for the camera and IR lighting and the shape information of the license plate into a previously learned learning model to obtain corrected posture information for the camera or IR lighting, and apply the corrected posture information to the vehicle license plate recognition device. Includes a control unit that transmits to .

A data collection unit that collects the front image of the vehicle captured from the cameras installed in the plurality of license plate recognition devices, the posture information corrected for the camera and IR lighting corresponding to the front image, respectively, and the front image of the vehicle, It may further include a learning unit for training the learning model by inputting a dataset consisting of input data including shape information of the license plate obtained from the front image and output data including corrected posture information of the camera and IR lighting. You can.

The shape information of the license plate includes shape information including any one of the slope, position, and size of the license plate area obtained around a reference line set in the horizontal or vertical direction of the front image of the vehicle, and the shape information included in the license plate area. Can contain brightness values of all pixels.

The control unit may obtain the pan angle, tilt angle, and rotation angle to be corrected from the basic posture, respectively, according to the shape information of the license plate.

The control unit may obtain the pan angle and tilt angle for the IR lighting to be corrected from the basic posture of the IR lighting in response to each corrected pan angle and tilt angle for the camera.

The control unit may adjust the illuminance value of IR lighting by comparing the brightness value of all pixels included in the license plate area with a preset reference brightness value.

The control unit controls to lower the illuminance value of IR lighting when the average brightness value for all pixels included in the license plate area is higher than the reference brightness value, and the average brightness value for all pixels included in the license plate area is lower than the reference brightness value. If it is lower than this value, the illuminance value of IR lighting can be controlled to increase.

The control unit controls the IR lighting to be turned off when the average brightness value for all pixels included in the license plate area is higher than a threshold value, and the threshold value may have a value higher than the reference brightness value.

In addition, according to an embodiment of the present invention, in the vehicle number recognition control method using a vehicle number recognition control system, the steps of acquiring basic attitude information about cameras and IR lights installed in a plurality of vehicle number recognition devices, the vehicle number recognition Receiving a front image of an approaching vehicle from a device, preprocessing the received front image to detect a license plate area, obtaining shape information of the license plate from the detected license plate area, and using the camera and IR lighting Input the basic posture information and the shape information of the license plate into a previously learned learning model to obtain corrected posture information for the camera or IR lighting, and transmit the corrected posture information to the license plate recognition device to obtain the camera or IR lighting. It includes the step of controlling the posture of.

According to the present invention, the posture of the camera or IR light can be corrected in real time according to the shape information of the license plate recognized using artificial intelligence, and can be controlled in real time according to the environment of each parking lot, thereby increasing the recognition rate of the license plate. You can. In addition, according to the present invention, it is possible to correct the posture of the camera and IR lighting without having to deploy professional manpower on site, which is effective in reducing labor costs.

Figure 1 is a configuration diagram of a license plate recognition control system according to an embodiment of the present invention.
Figure 2 is a perspective view for explaining the vehicle license plate recognition device shown in Figure 1.
FIG. 3 is a diagram for explaining a camera installed in the license plate recognition device shown in FIG. 2.
FIG. 4 is a diagram for explaining the IR lighting installed in the license plate recognition device shown in FIG. 2.
FIG. 5 is a configuration diagram for explaining the posture control server shown in FIG. 1.
Figure 6 is a flowchart for explaining a method of controlling a vehicle number recognition device using a vehicle number recognition control system according to an embodiment of the present invention.
FIG. 7 is a flowchart for explaining step S610 shown in FIG. 6.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. In this process, the thickness of lines or sizes of components shown in the drawing may be exaggerated for clarity and convenience of explanation.

Additionally, the terms described below are terms defined in consideration of functions in the present invention, and may vary depending on the intention or custom of the user or operator. Therefore, definitions of these terms should be made based on the content throughout this specification.

Hereinafter, the license plate recognition control system according to an embodiment of the present invention will be described in more detail using FIG. 1.

Figure 1 is a configuration diagram of a license plate recognition control system according to an embodiment of the present invention.

As shown in FIG. 1, the license plate recognition control system according to an embodiment of the present invention includes a plurality of license plate recognition devices 100 and a posture control server 200.

First, the plurality of license plate recognition devices 100 are installed on one side of the parking lot and are devices that recognize license plates of entering or exiting vehicles using cameras and IR lighting. The license plate recognition device 100 transmits the captured front image of the vehicle and basic attitude information about the camera and IR lighting to the attitude control server 200.

Next, the posture control server 200 uses the front image of the vehicle received from the license plate recognition device 100 to obtain corrected posture information for the camera and IR lighting. To elaborate, the posture control server 200 trains a learning model to output posture information corrected for the camera and IR lighting. Next, the front image of the vehicle received from the license plate recognition device 100 is input to the learned model to obtain corrected posture information for the camera and IR lighting, and the obtained corrected posture information is used for license plate recognition. delivered to the device 100. Then, the license plate recognition device 100 corrects the posture of the camera and IR lighting using the received corrected posture information, and rephotographs the license plate of the entering or exiting vehicle while maintaining the corrected posture.

Hereinafter, the license plate recognition device 100 shown in FIG. 1 will be described in more detail using FIGS. 2 to 4.

FIG. 2 is a perspective view for explaining the vehicle number recognition device shown in FIG. 1, FIG. 3 is a view for explaining a camera installed in the vehicle number recognition device shown in FIG. 2, and FIG. 4 is a view for explaining the vehicle shown in FIG. 2. This is a drawing to explain the IR lighting installed in the number recognition device.

As shown in FIG. 2, the license plate recognition device 100 is formed in the shape of a square pillar, and on the inside is a camera 110 that photographs the front of the vehicle and a camera 110 that radiates infrared waves and increases the sensitivity of the camera 100. Includes IR illumination (120). In addition, the upper side of the license plate recognition device 110 includes an output unit 130 that outputs the license plate number obtained from the front image of the vehicle captured through the camera 100.

First, as shown in FIG. 3, the camera 110 is installed on one side of the license plate recognition device 100. At this time, the camera 110 is preferably installed to pan, tilt, and roll to increase the recognition rate of the side panel of an entering vehicle.

The camera 110 is fixed to the holder 112 located above the fixing part 111. The holder 112 is fixed to the fixing unit 110 by a first rotation shaft (not shown), and the first rotation shaft rotates the holder 112 in the left and right directions using power received from the motor. In addition, both ends of the holder 112 include a third rotation axis (not shown) that fixes the camera, and the rotation axis rotates the camera 110 in the vertical direction by power received from the motor.

And, as shown in FIG. 3, the embodiment of the present invention further includes a third rotation axis 113 on the bottom of the fixing part 110. The third rotation axis 113 rotates the fixing part 110. Accordingly, the camera 110 is rotated circularly using the third rotation axis 113.

In addition, the IR light 120 is installed on one side of the camera 110 and radiates light to the entering or exiting vehicle, and is panned or tilted according to the rotation direction of the camera 110.

To elaborate, as shown in 4, the IR illumination 120 includes a plurality of IR LEDs. And, like the camera 110, the IR illumination 120 is fixed by the holder 122 located above the fixing part 121. At this time, the holder 122 is rotated left and right by a rotation axis (not shown) connected to the fixing part 121. Additionally, the IR lighting 120 is fixed by a rotating shaft (not shown) installed at both ends of the holder 122, and the rotating shaft rotates the IR lighting 120 in the up and down direction.

In an embodiment of the present invention, the camera 110 is panned, tilted, and rolled using the corrected posture information received from the posture control server 200. Additionally, the IR light 120 is panned and tilted using the corrected posture information received from the posture control server 200.

In the embodiment of the present invention, the camera 110 and the IR light 120 are described as being installed separately. The camera 110 and IR lighting 120 may be installed simultaneously in one housing. At this time, rather than controlling the postures of the camera 110 and the IR lighting 120 separately, the postures of the camera 110 and the IR lighting 120 are controlled simultaneously.

Hereinafter, the posture control server 200 will be described in more detail using FIG. 5.

FIG. 5 is a configuration diagram for explaining the posture control server shown in FIG. 1.

As shown in FIG. 5, the posture control server 200 according to an embodiment of the present invention includes a posture information acquisition unit 210, an image reception unit 220, a license plate recognition unit 230, a data collection unit 240, It includes a learning unit 250 and a control unit 260.

First, the posture information acquisition unit 210 acquires basic posture information about the camera 110 and IR lighting 120 installed inside from the plurality of license plate recognition devices 100. To elaborate, the license plate recognition device 100 is installed on one side of the space where entering or leaving vehicles proceed. Therefore, depending on the location and location where the license plate recognition device 100 is installed, the camera 110 for photographing the front of the vehicle and the IR lighting 120 installed to increase photographing sensitivity are set to a preset height and rotation angle.

Accordingly, the posture information acquisition unit 210 acquires basic posture information about the camera 110 and the IR light 120 set at the current point of view. The basic posture information includes at least one of height, rotation angle in the left and right directions, and rotation angle in the up and down directions.

The image receiver 220 receives the front image of the vehicle captured by the camera 110. At this time, the front image of the vehicle represents an image captured through the camera 110 and IR lighting 120 set to the basic posture.

Next, the license plate recognition unit 230 obtains information about the shape of the license plate from the front image of the vehicle.

To elaborate, the license plate recognition unit 230 preprocesses the received front image, detects the license plate area, and then obtains information about the shape of the license plate from the detected license plate area.

Here, the shape information of the license plate includes shape information including any one of the slope, position, and size of the license plate area, and the brightness value of all pixels included in the license plate area.

The data collection unit 240 collects front images of the vehicle received from a plurality of license plate recognition devices 100. Additionally, the data collection unit 240 collects basic posture information or corrected posture information of the camera 110 and IR light 120 installed in the license plate recognition device 100 in response to the front image of the vehicle.

Next, the learning unit 250 trains a learning model using the collected front image of the vehicle, the corrected posture information of the camera 110, and the IR light 120. To elaborate, the learning unit 250 outputs input data including the front image of the vehicle and license plate shape information extracted from the front image, and output data including the corrected posture information of the camera 110 and IR light 120. Create a structured dataset. Next, the learning unit 250 inputs the generated dataset into the learning model and trains the learning model to output corrected posture information.

Finally, the control unit 260 inputs the received front image of the vehicle into the learning model for which learning has been completed to obtain corrected posture information corresponding to the front image of the vehicle, and applies the obtained corrected posture information to the corresponding license plate recognition device ( 100).

Hereinafter, using FIGS. 6 and 7, a method of controlling the posture of the camera and IR lighting installed in the license plate recognition device using the license plate recognition control system according to an embodiment of the present invention will be described in more detail.

Figure 6 is a flowchart for explaining a method of controlling a vehicle number recognition device using a vehicle number recognition control system according to an embodiment of the present invention.

As shown in FIG. 6, the posture control server 200 according to an embodiment of the present invention trains the constructed learning model (S610).

FIG. 7 is a flowchart for explaining step S610 shown in FIG. 6.

As shown in FIG. 7, first, the posture control server 200 receives the front image of the vehicle from a plurality of license plate recognition devices 100 and the camera 110 and IR light 120 installed on the license plate recognition device 100. ) receives the corrected posture information (S611).

The license plate recognition device 110 uses the camera 110 and IR lighting 120 set to the basic posture to photograph the front of a vehicle entering the parking lot toward the entrance. And, if it is determined that it is impossible to recognize the vehicle's license plate number using the front image of the vehicle, conventionally, the manager who manages the license plate recognition device 110 manually corrects the posture of the camera 110 and the IR light 120. did.

The posture control server 200 according to an embodiment of the present invention does not require the administrator to individually correct the posture of the camera 110 and the IR light 120, but rather allows the learning model to determine the camera 110 from the input front image of the vehicle. ) and the purpose is to obtain corrected posture information of the IR light 120.

Therefore, the posture control server 200 receives the front image of the vehicle obtained by conventionally photographing the front of the vehicle and the corrected posture information of the camera 110 and IR light 120 from the license plate recognition device 110. .

At this time, the received front image of the vehicle represents an image captured with the camera 110 and IR lighting 120 installed in the license plate recognition device 100 in their basic positions. In addition, the attitude information of the camera 110 includes the rotation angle of the camera 110 with respect to the pan, the rotation angle with respect to the tilt, and the rotation angle with respect to the rotation, and the attitude information of the IR light 120 includes the rotation angle with respect to the pan. , rotation angle for tilt, and brightness value of the light.

The received front image of the vehicle and the corrected posture information of the camera 110 and IR light 120 installed in the license plate recognition device 100 are stored in the data collection unit 240.

Next, the license plate recognition unit 230 obtains the shape information of the license plate from the received front image of the vehicle (S613)

To elaborate, the license plate recognition unit 230 preprocesses the received front image of the vehicle and then detects the license plate area. Then, the license plate recognition unit 230 acquires shape information of the license plate area and brightness values of all pixels included in the rear plate area centered on a preset horizontal or vertical reference line.

Here, the shape information includes any one of the slope, position, and size of the license plate area.

In detail, the location of the license plate is different depending on the type of vehicle, the driving direction of the vehicle may be biased to one side of the space, or the shape of the license plate displayed on the front image of the vehicle may be different depending on the rotation angle of the vehicle. Accordingly, the license plate recognition unit 230 sets a baseline and extracts shape information of the license plate centered on the baseline.

Additionally, the license plate recognition unit 230 acquires the brightness values of all pixels included in the license plate area.

Next, the learning unit 250 uses the front image of the vehicle stored in the data collection unit 240, the shape information of the license plate obtained from the front image of the vehicle, and the camera 110 and IR lighting installed in the license plate recognition device 100. A dataset is created using the corrected posture information in (120) (S613).

To elaborate, the learning unit 250 uses the front image of the vehicle and the shape information of the corresponding license plate as input data, and the corrected posture information of the camera 110 and IR light 120 corrected by the manager as output data. Create a dataset consisting of

Next, the learning unit 250 inputs the generated dataset into the learning model and trains the learning model to output corrected posture information for the camera 110 and IR light 120 (S614).

In detail, the learning unit 250 supervised learning a learning model using a dataset consisting of input data and output data. Then, when the learning model receives the front image of the vehicle, it outputs corrected posture information for the camera 110 and IR lighting 120.

When step S610 is completed, the image receiver 220 receives image information of the vehicle captured from one of the plurality of license plate recognition devices 100 (S620).

To elaborate, the license plate recognition device 100 uses the camera 110 and the IR light 120 set to the basic posture to photograph the front of the vehicle entering or exiting the vehicle. Then, the license plate recognition device 100 transmits the captured front image of the vehicle to the attitude control server 200. At this time, the license plate recognition device 100 may transmit basic attitude information of the camera 110 and IR lighting 120 installed inside along with the front image of the vehicle.

Next, the license plate recognition unit 230 obtains information on the shape of the license plate from the received front image of the vehicle (S630)

To elaborate, the license plate recognition unit 230 preprocesses the received front image of the vehicle and then detects the license plate area. Then, the license plate recognition unit 230 acquires shape information including any one of the slope, position, and size of the license plate area around a preset horizontal or vertical reference line. Additionally, the license plate recognition unit 230 acquires the brightness values of all pixels included in the license plate area.

Next, the control unit 260 acquires posture information about the camera 110 and the IR light 120 from the learning model by inputting it into the learning model on which learning has been completed (S640).

To elaborate, the control unit 260 inputs the front image of the vehicle and the shape information of the license plate into the learning model that has completed learning. Then, the learning model acquires posture information about the camera 110 and IR light 120 to be corrected from the input front image of the vehicle and the shape information of the license plate.

When step S640 is completed, the control unit 260 determines the corrected posture for the camera 110 and the IR light 120 from the posture information to be corrected for the camera 110 and the IR light 120 obtained through the learning model. Obtain information (S650).

To elaborate, the control unit 260 obtains the pan angle, tilt angle, and rotation angle to be corrected according to the shape information of the license plate. Then, the control unit 260 obtains the corrected pan angle, tilt angle, and rotation angle by applying the pan angle, tilt angle, and rotation angle to be corrected to the basic posture of the corresponding camera 110 and IR light 120. .

Next, the control unit 260 sets a pan angle for the IR light 120 to be corrected from the basic posture of the IR light 120 in response to each corrected angle for the pan angle and tilt angle for the camera 110. and obtain the tilt angle.

The control unit 260 transmits the corrected posture information about the camera 110 and the IR light 120 to the corresponding license plate recognition device 100.

Additionally, the control unit 260 sets a reference brightness value for the brightness value and controls the illuminance value of the IR lighting 120 using the set reference brightness value (S660).

The control unit 260 obtains the average brightness value for all pixels included in the license plate area and compares the obtained average brightness value with the reference brightness value.

And, if the reference brightness value is higher than the average brightness value, the control unit 260 controls the illuminance value of the IR lighting 120 to be lowered. On the other hand, if the reference brightness value is lower than the average brightness value, the controller 260 controls the illuminance value of the IR lighting 120 to increase.

Meanwhile, the control unit 260 controls the IR lighting to turn off when the average brightness value for all pixels included in the license plate area is higher than the threshold value. Here, the threshold represents a value higher than the reference brightness value.

According to the license plate recognition control system according to the present invention, the posture of the camera or IR light can be corrected in real time according to the shape information of the license plate recognized using artificial intelligence, and can be controlled in real time according to the environment of each parking lot. Therefore, the recognition rate for license plates can be increased. In addition, according to the present invention, it is possible to correct the posture of the camera and IR lighting without having to deploy professional manpower on site, which is effective in reducing labor costs.

The present invention has been described with reference to the embodiments shown in the drawings, but these are merely illustrative, and those skilled in the art will understand that various modifications and other equivalent embodiments are possible therefrom. will be. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the patent claims below.

100: Vehicle number recognition device
200: Attitude control server
210: Attitude information acquisition unit
220: video receiver
230: License plate recognition unit
240: data collection unit
250: Learning Department
260: control unit

Claims (16)

In the vehicle number recognition control system using artificial intelligence,
A data collection unit that collects the front image of the vehicle captured from cameras installed in a plurality of license plate recognition devices and the corrected posture information for the camera and IR lighting corresponding to the front image, respectively;
A dataset consisting of input data including the front image of the vehicle and shape information of the license plate obtained from the front image, and output data including corrected posture information of the camera and IR lighting is input to the learning model and trained. learning department,
An attitude information acquisition unit that acquires basic attitude information about the cameras and IR lights installed in the plurality of license plate recognition devices,
An image receiver that receives a front image of an approaching vehicle from the license plate recognition device,
A license plate recognition unit that preprocesses the received front image to detect a license plate area and obtains shape information of the license plate from the detected license plate area, and
Input basic posture information for the camera and IR lighting and shape information of the license plate into the learning model to obtain corrected posture information for the camera or IR lighting, and transmit the corrected posture information to the license plate recognition device. Includes a control unit,
The control unit,
Acquire the pan angle, tilt angle, and rotation angle to be corrected from the basic posture according to the shape information of the license plate, respectively,
A license plate recognition control system that acquires the pan angle and tilt angle for the IR light to be corrected from the basic posture of the IR light in response to each corrected angle for the pan angle and tilt angle for the camera. delete According to paragraph 1,
The shape information of the license plate is,
Shape information including any one of the inclination, position, and size of the license plate area obtained around a reference line set in the horizontal or vertical direction of the front image of the vehicle;
A vehicle license plate recognition control system including brightness values of all pixels included in the license plate area. delete delete According to paragraph 3,
The control unit,
A vehicle license plate recognition control system that adjusts the illuminance value of IR lighting by comparing the brightness value of all pixels included in the license plate area with a preset reference brightness value. According to clause 6,
The control unit,
If the average brightness value of all pixels included in the license plate area is higher than the reference brightness value, the illuminance value of the IR lighting is controlled to be lowered,
A vehicle license plate recognition control system that controls to increase the illuminance value of IR lighting when the average brightness value of all pixels included in the license plate area is lower than the reference brightness value. In clause 7,
The control unit,
Controlling the IR lighting to turn off when the average brightness value for all pixels included in the license plate area is higher than a threshold value,
The threshold value is a vehicle number recognition control system having a value higher than the reference brightness value. In the vehicle number recognition control method using a vehicle number recognition control system,
Collecting corrected posture information for the front image of the vehicle captured from cameras installed in a plurality of license plate recognition devices, and the camera and IR lighting corresponding to the front image, respectively;
A dataset consisting of input data including the front image of the vehicle and shape information of the license plate obtained from the front image, and output data including corrected posture information of the camera and IR lighting is input to the learning model and trained. step,
Obtaining basic posture information about cameras and IR lights installed on the plurality of license plate recognition devices,
Receiving a front image of an approaching vehicle from the license plate recognition device
preprocessing the received front image to detect a license plate area, and obtaining shape information of the license plate from the detected license plate area; and
Basic posture information for the camera and IR lighting and shape information of the license plate are input to the learning model to obtain corrected posture information for the camera or IR lighting, and the corrected posture information is transmitted to the license plate recognition device. Controlling the pose of a camera or IR light,
The step of controlling the posture of the camera or IR light is,
Acquire the pan angle, tilt angle, and rotation angle to be corrected from the basic posture according to the shape information of the license plate, respectively,
A vehicle number recognition control method for obtaining pan angles and tilt angles for IR lighting to be corrected from the basic posture of IR lighting in response to each corrected angle for the pan angle and tilt angle for the camera. delete According to clause 9,
The shape information of the license plate is,
Shape information including any one of the inclination, position, and size of the license plate area obtained around a reference line set in the horizontal or vertical direction of the front image of the vehicle;
A vehicle license plate recognition control method including brightness values of all pixels included in the license plate area. delete delete According to clause 11,
The step of controlling the posture of the camera or IR light is,
A vehicle license plate recognition control method that adjusts the illuminance value of IR lighting by comparing the brightness value of all pixels included in the license plate area with a preset reference brightness value. According to clause 14,
The step of controlling the posture of the camera or IR light is,
If the average brightness value of all pixels included in the license plate area is higher than the reference brightness value, the illuminance value of the IR lighting is controlled to be lowered,
A vehicle number recognition control method that controls to increase the illuminance value of IR lighting when the average brightness value for all pixels included in the license plate area is lower than the reference brightness value. According to clause 15,
The step of controlling the posture of the camera or IR light is,
Controlling the IR lighting to turn off when the average brightness value for all pixels included in the license plate area is higher than a threshold value,
A vehicle number recognition control method wherein the threshold value has a value higher than the reference brightness value.