KR20160061132A - Apparatus and method for recognizing the number of cars and a computer-readable recording program for performing the said method, the recording medium - Google Patents

Abstract

The present invention relates to an apparatus and a method for recognizing number plates, and a computer-readable recording medium for recording program for performing the method. As one aspect, the apparatus for recognizing number plates comprises: an illumination analysis unit which captures images for illumination analysis on the basis of loop-sensing signals within a range of capturing a vehicle to enter when the vehicle enters, and analyzes an area wherein a number plate is located and a vehicle color, in order to calculate illumination values within a selection range; a shutter controlling unit which controls shutting operations of a capturing unit within a recognition range of the number plate, on the basis of the calculated illumination values, to capture images for recognition of the number plate; and a number plate recognition unit which reads the captured image for the number plate recognition and recognizes the number plate of a vehicle to enter. According to the technical characteristics, the apparatus captures images without generating of backlight, reflected lights and the like in the daytime, regardless of a location wherein the apparatus is installed, and is able to clearly read the number plate from the captured images. In addition, the apparatus can capture images to clearly read the number plate without generating of smear and mirror phenomena when a diffuse reflection from a sidelight or car headlight occurs. The apparatus can effectively recognize a number plate when a number plate is not recognized from natural phenomenon such as snow or rain, when a filth falls on a number plate while driving on the road, or when a number plate is illegally altered or painted such that the front number plate cannot be recognized.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus and method for recognizing a car number and a computer readable recording medium storing a program for performing the method.

In the present invention, when the front and rear license plates of the vehicle are photographed and the vehicle number is recognized, when the afterglow (backlight, reflected light, light metering) occurs due to the illuminance change of the photographing area, the light source angle change, Even in a variety of environments where it is difficult to recognize the vehicle number, for example, when only the equipment is affected by shadows, when shadows are generated only in the area where the vehicle is photographed, when mirror reflection or smear occurs due to diffused reflection of the headlights at night And a computer readable recording medium storing a program for carrying out the method.

The number plate of a vehicle is a unique number assigned to each vehicle to give different identification, and it is a unique number assigned to each vehicle, such as the type of vehicle, manufacturer, production period, use purpose, displacement, prime mover type, owner, dwelling place, invincible vehicle, And so on. Therefore, it is very important to recognize the car number quickly and accurately in any car number inquiry environment.

Vehicle number recognition technology is a technology to recognize a vehicle number from a license plate. It is applied to a control system of a parking management facility, and it is widely used for monitoring input / output vehicles through the non-issuance entry method, , And is also widely used to crack down on road traffic violations such as lane violations, signal violations, and speed violations.

However, in the conventional vehicle identification technology, when the vehicle front surface license plate can not be recognized due to snow, rain, dirt, or the like, or when a smear phenomenon occurs due to reflection of sunlight on a side portion of a vehicle body, There is a limit that the recognition rate of the car number is greatly deteriorated when diffused reflection occurs by the vehicle light.

For example, in order to recognize the car number entering the parking lot entrance, the car number recognition device can only shoot images in a direction far from the designated position of the parking lot entrance. In particular, in the daytime, the location and brightness of the sunlight, Since it is influenced by various shadows, it has many negative effects on the image to be photographed.

In addition, reflected light (Miller) phenomenon appears due to the external color or plate color of the entering vehicle, or when the backlight is generated, the image of the vehicle number can not be recognized because of the influence of the shadow.

In addition, due to the change of the surrounding environment due to snow or rain, the license plate of the vehicle is blocked, the license plate is not recognized due to dirt throwing or the like, or the smear phenomenon And the recognition rate of the car number is greatly lowered. Furthermore, at night, it is very limited in recognizing the license plate of the vehicle due to diffused reflection by the vehicle light.

In order to solve such a problem, Patent Document KR10-2010-0112004 discloses "a vehicle number recognition system using a dual camera and a method thereof ".

Briefly, "a vehicle number recognition system using a dual camera" includes a vehicle detection unit for detecting a vehicle entering a vehicle detection area; A light emitter for emitting infrared light to the vehicle sensing area; A first camera employing an infrared ray pass filter for taking an image in cooperation with the transparent portion; A second camera employing an infrared cut filter; A database for setting camera information to be used for photographing the vehicle; A switching unit for switching according to a control signal to drive at least one of the first and second cameras; A car number recognition unit for recognizing a car number constituted by letters and numbers in an image photographed by the first and second cameras; A storage unit for storing an image taken by the first and second cameras and a recognized car number; And outputs a control signal for driving at least one of the first camera and the second camera to the switching unit according to camera information set in the database when recognizing the vehicle entry into the vehicle detection area according to the detection signal of the vehicle detection unit, And a control unit for controlling the operation of storing the vehicle number recognized by the number recognition unit in the storage unit.

With this configuration, the patent discloses a method of selecting a camera to be used for shooting with a camera ID set in the database or a camera to be used for shooting according to the illuminance measured by an illuminance sensor, or taking into consideration both the measurement illuminance of the database and the illuminance sensor Select the camera to be used for shooting. That is, by comparing the illuminance measured by the illuminance sensor with the reference value, the photographing portion to be used in the photographing is selected. Thus, the recognition rate of the vehicle number is improved by acquiring a high quality image without being restricted to the surrounding environment.

However, the technology proposed in the above-mentioned patent discloses that, as in the above-mentioned existing technology, the front plate of the vehicle can not be recognized due to snow, rain, dirt throwing or the like, or the smear There is a limit in that the recognition rate of the vehicle number is extremely lowered when a phenomenon occurs or when a diffuse reflection occurs due to a vehicle light at night.

Therefore, there is a great demand for a technology capable of quickly and accurately recognizing the car number even in the case of any car number recognition environment change.

Korean Patent Publication No. 10-2010-0112004

The present invention relates to a car number recognition apparatus and method for solving the conventional problems, and a computer-readable recording medium on which a program for carrying out the method is recorded,

A vehicle number recognizing device and method thereof capable of capturing an image in which the installation position of the vehicle number recognizing device is restricted due to the generation of shadows due to buildings or objects in the vicinity during the daytime or in which no backlight or reflected light occurs during the daytime, It is another object of the present invention to provide a computer readable recording medium on which a program for carrying out the above method is recorded.

A vehicle number recognizing device and method capable of shooting images in which smear phenomenon and mirror phenomenon do not occur even when photometry or headlight diffuse reflection occurs, and a computer readable recording medium recording a program for performing the method .

In addition, if the vehicle license plate is blocked due to snow or rain due to natural phenomena, if the license plate is struck on the license plate while driving on the road, the license plate of the vehicle is illegally modified or illegally painted, The present invention aims to provide a vehicle number recognition apparatus and method which do not cause a decrease in recognition rate and an error at the time of recognition of a vehicle number even when the vehicle number can not be recognized and a computer readable recording medium on which a program for carrying out the method is recorded .

The present invention also relates to a vehicle number recognition apparatus and method for improving energy efficiency by not turning on an infrared (IR) illumination with the highest power consumption during a day except for night and dark days, and a computer readable recording medium And to provide the above-mentioned objects.

According to an aspect of the present invention, there is provided an apparatus for car number recognition,

At least one photographing section for photographing an image of an incoming vehicle on the basis of a loop detection signal within an incident photographing range; An illuminance analyzer for analyzing an area where a license plate is located and a vehicle color with respect to the photographed image and calculating an illuminance value within a selected range; A shutter control unit for controlling the shutter operation of the photographing unit based on the calculated illuminance value and capturing an image for recognizing the vehicle number; And a car number recognizing unit for recognizing the car number of the incoming car by reading the photographed car number recognition image.

In one aspect, the illuminance analyzing unit sets an illuminance recognition range around the license plate for analyzing the area where the license plate is located and the color of the vehicle in the photographed image.

In one aspect, the image of the entering vehicle and the image of recognizing the car number are photographed at the front and rear portions of the vehicle. The vehicle number recognizing unit recognizes the vehicle number from the vehicle number recognizing image photographed at the rear side of the vehicle when the vehicle number is not recognized from the vehicle number recognizing image. For example, both front and rear license plates are photographed for roughness analysis, and the illuminance of the part where the license plate is located in the entire image range is analyzed to identify license plate through high-speed arithmetic calculation It is possible to recognize the vehicle number by photographing the secondary image for recognizing the car number after changing to the optimum shutter range.

In one aspect, the shutter control unit integrally analyzes the shutter position, the maximum and minimum illuminance values, the image amplification value, and the maximum shutter movement value of the photographing unit based on the calculated illuminance values, And when the shutter value analyzed is smaller than the shutter value at the time of shooting, the shutter opening / closing control of the shutter of the shooting section is controlled by the difference value.

The illuminance analyzing unit takes an image for illuminance analysis around the license plate before photographing the car number recognition image when detecting the vehicle. By analyzing the license plate color, reflection illuminance, automobile color, and reflection illuminance of the area where the car number is located, The shutter speed value that is closest to moving the resolution and clarity to the optimum range is calculated and moved to that value quickly.

At this time, the range of the predicted area including the license plate is set so that only the image of the license plate portion can be seen clearly in the image captured when the image for illuminance analysis is taken on the front surface or the rear surface of the vehicle.

The shutter control unit analyzes a minimum illumination value and a maximum illumination value of the previously moved shutter position and a preset minimum exposure intensity value and determines a minimum illumination value and a maximum illumination value The image brightness, the image brightness, and the like to analyze how much the shutter is opened and closed, and instantaneously move the shutter of the photographing unit based on the result, Definition), the illumination for the vehicle identification is changed by changing the illuminance of the entire screen range to the illuminance around the license plate.

If it is judged that it is a daytime, it is not necessary to turn on the IR (Infrared Ray) lamp. If it is judged at night, turn on the IR lamp and recognize the car number. And recognizes the vehicle number.

If the vehicle number is not recognized even though the image number of the license plate part is recognized and the image quality is changed (Image Quality Modification), it is illegal to renovate license plate, use illegal paint, It is judged that car number analysis is impossible due to dirt burning due to snow / rain, speed, diffused headlights of car headlights, wrinkles on license plates, etc., and the image of the front face license plate is discarded and the rear face license plate is photographed. If the car number is recognized and still not recognized, the captured rear image is saved.

Also, when the illuminance of the location where the vehicle number recognition device is installed and the image of the current vehicle are taken, there is an error in recognition of the vehicle number because the illuminance differs according to the location and the time zone. According to the present invention, the vehicle image of the current entry position is photographed and analyzed so as to operate irrespective of the position where the vehicle number recognition apparatus is installed, and based on the result, The illuminance of the whole image is changed with the same illuminance, and the most suitable image is recognized for the car number recognition. According to these technical features, the present invention can acquire a high-quality image for recognizing the car number irrespective of the installation position of the car number recognizer and various natural phenomenon changes.

Meanwhile, a method for car number recognition according to the present invention includes:

(A) setting an illuminance recognition range around the license plate for analyzing the area where the license plate is located and the vehicle color in the photographed image; (B) photographing an image for illuminance analysis based on a loop detection signal within an incident range when the vehicle enters the vehicle; (C) calculating an illuminance value within a selected range by analyzing an area where the set number plate is located and a vehicle color; (D) capturing an image for vehicle number recognition by controlling the shutter operation of the photographing section in the recognition range of the license plate based on the calculated illuminance value; And (E) reading the photographed image for recognizing the car number to recognize the car number of the incoming car.

In one aspect, the vehicle number recognizing method includes the step of controlling ON / OFF of the infrared lamp based on the illuminance value in the selection range when photographing the illuminance analysis image. For example, if the illuminance around the license plate is recognized as daylight, turn off the infrared (IR) lamp.

In one aspect, a vehicle number recognition method includes recognizing a vehicle number from a vehicle number recognition image photographed at a rear portion of the vehicle when the vehicle number is not recognized from the vehicle number recognition image photographed at the front surface of the vehicle.

In one aspect, a car number identification method comprises: recognizing RFID CARD information from an entry vehicle; Requesting a registration inquiry to the car number management server for the recognized RFID CARD information; And recognizing, as the number of the incoming vehicle, the vehicle number recognized in the vehicle number recognized for the vehicle number and the vehicle number recognized through the registration inquiry when the inquiry result is the same vehicle number as the vehicle number recognized from the vehicle number recognition image .

In one aspect of the present invention, there is provided a car number recognition method comprising: a car number recognition image taken at a front part of a vehicle; a car number recognition image photographed at a front part of the car, And recording and storing an image for recognizing the car number photographed at the rear side of the vehicle.

The car number identification method according to the present invention is implemented as a program command and executed on a computer readable recording medium.

The vehicle number recognizing apparatus and method, and the computer readable recording medium recording the program for carrying out the method,

It is possible to shoot an image in which backlight or reflected light does not occur in the daytime regardless of the installation position of the vehicle number recognition device and the vehicle number can be stably read out from the photographed image.

In addition, even when metering or headlight diffuse reflection occurs, images without smear phenomenon and Miller phenomenon can be taken and the vehicle number can be reliably read.

In addition, if the vehicle license plate is blocked due to snow or rain due to natural phenomena, if the license plate is struck on the license plate while driving on the road, the license plate of the vehicle is illegally modified or illegally painted, The vehicle number can be recognized effectively even if it can not be recognized.

In addition, since the light source is moved differently according to the seasonal time zone where the car number recognizer is installed, the illuminance is analyzed on the license plate position in the image captured even by the partial shadow influence by surrounding buildings and objects, There is no occasion to affect.

In addition, when the illuminance around the license plate is recognized as the daytime, the infrared (IR) lamp power is turned off, and energy savings of up to 48% can be expected.

1 is a block diagram showing the configuration of a vehicle identification apparatus according to an embodiment of the present invention.
2 is a block diagram showing a configuration of a vehicle identification apparatus according to an embodiment of FIG.
3 is a flowchart illustrating a vehicle number recognition method according to an embodiment of the present invention.
4 is a flowchart illustrating a method of setting a map for photographing an image for roughness analysis according to an embodiment of the present invention.
5 is a flowchart illustrating a method of controlling opening and closing of a shutter based on an illuminance analysis value of an image according to an embodiment of the present invention.
6 is a flowchart illustrating a method for controlling a circuit breaker based on vehicle number information detected by a vehicle number recognizing apparatus and an RF reader according to an embodiment of the present invention.
FIG. 7 is a diagram illustrating an example of reflected light, meteorological light, and backlight generated according to one embodiment of the present invention.
FIG. 8 is an exemplary diagram showing a range setting range for illuminance analysis on the entire photographing range screen of the vehicle front-rear part according to an embodiment of the present invention. FIG.

The present invention is applicable to a case in which a front face plate of a vehicle can not be recognized due to snow, rain, dirt throwing, or the like, a smear phenomenon caused by sunlight reflected in a side part of a vehicle body part, The present invention relates to a car number recognition apparatus and a car navigation system, and a computer readable recording medium on which a program for carrying out the method is recorded.

To this end, the vehicle number recognition apparatus according to the present invention photographs an image for roughness analysis based on a loop detection signal within an incident range when the vehicle enters the vehicle, analyzes the area where the license plate is located and the vehicle color to calculate the illuminance value in the pre- An illuminance analysis unit; A shutter control unit for controlling the shutter operation of the photographing unit based on the calculated illuminance value and capturing an image for recognizing the vehicle number; And a car number recognizing unit for recognizing the car number of the incoming car by reading the photographed car number recognition image.

According to the present invention, there is provided an apparatus for recognizing a vehicle number, a method for identifying the same, and a computer-readable recording medium on which a program for performing the method is recorded, Can be photographed, and the vehicle number can be stably read out from the photographed image.

In addition, even when metering or headlight diffuse reflection occurs, images without smear phenomenon and Miller phenomenon can be taken and the vehicle number can be reliably read.

In addition, if the vehicle license plate is blocked due to snow or rain due to natural phenomena, if the license plate is struck on the license plate while driving on the road, the license plate of the vehicle is illegally modified or illegally painted, The vehicle number can be recognized effectively even if it can not be recognized.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the technical features of the present invention.

For the sake of clarity, reference will be made to the accompanying drawings, but repetitive description of the redundant configuration and detailed description of portions not related to the description are omitted. In the following description, a detailed description is omitted, and a detailed description thereof will be omitted for those skilled in the art.

Whenever a component is referred to as "including" an element throughout the specification and claims, it is understood that it may include other elements as well, without departing from the other elements unless specifically stated otherwise.

The present invention can be implemented in various forms based on the technical idea described in the claims. Therefore, the listed embodiments are only one example for understanding the technical idea of the present invention.

1 is a block diagram showing the configuration of a vehicle identification apparatus according to an embodiment of the present invention.

1, a vehicle number recognizing apparatus 100 according to the present invention includes a front photographing unit 110, a rear photographing unit 120, a front infrared lamp 130, a rear infrared lamp 140, and a control unit 150) And a computing unit (160).

The front loop detection signal detected when the vehicle enters the vehicle detection area serves as a sensing signal for photographing the front face of the vehicle and the rear loop detection signal serves as a sensing signal for photographing the rear face of the vehicle.

The front photographing unit 110 and the rear photographing unit 120 photograph the illuminance analysis image and the image of the car number recognition image around the front and rear license plates of the vehicle.

The control unit 150 maintains the ON / OFF control and the delay time (ON) of the front / rear loop detection signal reception, the front infrared lamp 130 and the rear infrared lamp 140 and outputs various command commands from the computing unit 160 And transmits the front / rear loop detection signal data. The front infrared ray lamp 130 and the rear infrared ray lamp 140 are illuminated with the flicker (i.e., red, green, and blue) at the time of receiving data analyzed at night by the front photographing unit 110 and the rear photographing unit 120, flicker) power supply signal.

2 is a block diagram showing a configuration of a vehicle identification apparatus according to an embodiment of FIG.

2, when a loop coil signal (vehicle detection data) for capturing a front / rear image of a vehicle is sensed, the computing unit 160 calculates a luminance analysis image And a flicker power signal for photographing the car number recognition image at a high speed.

The control unit 150 controls the operation of the front photographing unit 110 and the rear photographing unit 120 to photograph an image for roughness analysis based on the flicker power signal. At this time, the controller 150 performs roughness analysis only on a predetermined range, adds and subtracts a shutter value corresponding to the predetermined value, and controls the front and rear photographing units 110 and 120 ) To take a picture for vehicle number recognition.

When the car number is not recognized in the car number recognition image, the control unit 150 generates a flicker power signal to the rear image pickup unit 120 and the rear infrared ray lamp unit 140, And then carries out the image recognition of the vehicle number.

The front zooming lens 111 and the rear zooming lens 112 configure the focus of the image and the shooting range and resolution of the image according to the resolution. . ≪ / RTI >

The body of the front radiographing section 110 and the body of the rear radiographing section 120 include image sensors 112 and 122 for imaging an image and CPUs 113 and 123 for leading all functions of the radiographing section, And communication control units 114 and 124 for controlling various flicker power supply signals, so as to be able to shoot images, compress / store / transmit the photographed images, or adjust the illuminance (ISP).

The front infrared pass filter 115 and the rear infrared pass filter 125 block the visible light at all times and pass only the infrared wavelength and pass only the wavelength of the infrared light even when the front infrared lamp 130 and the rear infrared lamp 140 are turned on So that the focal distance is not changed according to the wavelength type of the light. In addition, due to the residual of the filter, diffuse reflection of light is generated and the image is formed by adopting a polarizing filter.

Meanwhile, the power supply unit 170 supplies switching power to the front photographing unit 110 and the rear photographing unit 120 to prevent the front photographing unit 110 and the rear photographing unit 120 from being blocked do.

The power supply unit 170 is configured to simultaneously supply various kinds of power sources, and the front infrared lamp 130 and the rear infrared lamp 140 are configured not to operate at the same time. In addition, by receiving a signal from the control unit 150 and supplying a high pressure of a flash system for a predetermined time (about 100 m / s), a sufficient amount of light is reflected on the vehicle and objects in a short time, do.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an operation of a car number recognition apparatus that operates with such a configuration will be described in detail with reference to the accompanying drawings.

When the vehicle enters the parking lot and a front loop detection signal is generated within the pickup range, the control unit 150 transmits the vehicle entry signal data to the computing unit 160.

The computing unit 160 transmits a flicker power signal for capturing an image of the front radiographing unit 110 to the controller 150 based on the vehicle entry signal data and the front radiographing unit 110 transmits the flicker power signal to the flicker flicker power source signal to the computing unit 160, and compresses and transmits the image.

The computing unit 160 analyzes the ambient illuminance of the license plate pre-registered in the compressed image data so that only the image of the surroundings of the license plate is illuminated by the front illuminating unit 110 (Open / close) of the shutter.

At this time, if the illuminance analyzed is below the minimum illuminance required for car number recognition, the controller 150 controls the operation of the front infrared lamp 130 so that the car number recognition image is turned on before shooting, .

When the computing unit 160 sends an instruction to the control unit 150 to photograph the number recognition image, the control unit 150 sends a flicker power signal to the front photographing unit 110 to photograph the image, And the computing unit 160 reads the photographed image and recognizes the car number.

If the rear loop detection signal is generated, the control unit 150 performs a luminance adjustment process in the same manner as the front image pickup unit 110 described above, and if necessary, And controls the 'On / Off' operation of the lamp 140 to recognize the rear vehicle number for the rear photographing unit 120.

If the car number is not recognized on both the front license plate and the rear license plate, the front part image is deleted and only the rear part image is recorded.

If it is determined at the nighttime that the illuminance around the license plate is analyzed, the computing unit 160 transmits a command signal to the controller 150 to photograph the image for car number recognition after turning on the front infrared ray lamp 130 and the rear infrared ray lamp 140 .

Meanwhile, according to an embodiment of the present invention, the car number identification device is installed in the parking control facility and can recognize the car number in association with the RFID device 200 during operation. For example, the RFID device 200 recognizes the RFID information from the vehicle entering the intrusion shooting range, and the corresponding vehicle number may be input. The computing unit 160 may recognize the input RFID information and the vehicle identification data at the same time Or only one of the same data within a predetermined time (pre-registered time) is recognized during the forwarding operation, and the image data is stored for various information analysis.

In one aspect, the photographed image and recognition information are stored in the car number management server 300, and can be selectively provided when a request is received for image data from various devices of the vehicle control facility.

The vehicle number recognizing apparatus 100 according to the present invention may include the illuminance analyzing unit 161, the shutter controlling unit 162 and the car number recognizing unit 163) Based on the sensing signal, the image captured by the front photographing unit 110 and the rear photographing unit 120 is analyzed for the area where the license plate is located and the vehicle color to calculate the illuminance value within the selected range. The illuminance analyzer 161 may set the area where the license plate is located and the illuminance recognition area around the license plate for analyzing the vehicle color in the images photographed by the front photographing part 110 and the rear photographing part 120. [

The shutter control unit 162 controls the shutter operation of the front photographing unit 110 and the rear photographing unit 120 based on the calculated illuminance value and captures the image for vehicle number recognition. The shutter control unit 162 analyzes the shutter position, the maximum and minimum illuminance, the image amplification value, and the maximum shutter value of the front photographing unit 110 and the rear photographing unit 120 based on the calculated illuminance value, When the analyzed shutter value is smaller than the shutter value or the shutter value analyzed compared to the shutter value at the shooting time is large, the shutter opening / closing control of the shooting unit is controlled by the difference value.

The car number recognizing unit 163 recognizes the car number of the entering car by reading the car number identification image photographed by the front photographing unit 110 and the rear photographing unit 120. [ The car number recognizing unit 163 recognizes the car number from the car number recognizing image photographed at the rear side of the vehicle when the car number is not recognized from the car number recognizing image photographed at the front side of the vehicle.

3 is a flowchart illustrating a vehicle number recognition method according to an embodiment of the present invention.

Referring to FIG. 3, a photographing range is set for each type of resolution of a photographing unit before photographing a light adjusting image. For example, it is possible to stop the vehicle within the intrusion shooting range where the front face loop detection of the vehicle is installed, view the real time image taken, set the shooting range with the zoom lens, and set the shooting distance and range.

After the shooting distance and the range are set, the area where the license plate is located and the illumination recognition area around the license plate for analyzing the vehicle color are set in advance (see FIG. 4).

If it is determined in step S311 that the shooting range for each type of resolution of the photographing unit and the illuminance recognition range for the license plate are completed, if the vehicle enters the intrinsic photographing range, the front photographing unit 110) photographs a vehicle front surface illuminance analysis image in step S313.

In step S314, the license plate and the color of the vehicle in the predetermined selection range are analyzed to calculate the illuminance value within the selection range in order to change and set the entire image illuminance so that only the license plate is recognized in the photographed image. S322), only the number plate moves the electronic shutter within a visible range based on the calculated illuminance value.

If the illuminance value within the selection result range is the daytime, it is determined whether the illuminance around the license plate is the illuminance in which the car number recognition is not possible or the illuminance is sufficient. (IR) lamp and the rear infrared (IR) lamp are turned on, the front panel car number analysis image and rear panel car number analysis image are taken.

If it is read at night, turn on the front infrared ray (IR) lamp and the rear infrared ray (IR) lamp, and shoot images for front panel car number analysis and rear panel car number analysis in steps S324_A and S324_B.

If it is determined in step S317 that the front and rear portions of the vehicle are recognized from the taken image of the front portion car number analyzing image and the rear portion car number analyzing image, the image data recognized for the front portion of the vehicle in step S318_A Is transmitted to the car number management server (300).

If the image is not recognized with respect to the front surface and the rear surface of the vehicle, the image data recognized for the front surface of the vehicle is deleted in step S319_A, and then the vehicle enters the intrinsic shooting range, The image for analyzing the rear car number is taken.

The image of the rear side car number analysis image is analyzed in the same manner as the image recognition process for the front side of the vehicle described above. When the image is normally recognized for the rear side of the vehicle, the image data is displayed in step S318_B, And is transmitted to the management server 300. If the image is not recognized with respect to the rear portion of the vehicle, the unrecognized rear portion image data is transmitted to the car number management server 300 in step S319_B.

Meanwhile, in an embodiment of the present invention, the car number recognition apparatus 100 is installed in a parking control facility and can recognize the vehicle number by being associated with the RFID device 200 during operation. For example, if the vehicle has the RFID CARD and the vehicle enters the entry shooting range, the RFID device 200 transmits the registered vehicle number confirmation procedure for the RFID information recognized in the RFID CARD to the vehicle number management server 300 If it is determined that the registered vehicle is the same registered car number recognition data recognized by the car number recognition device 100 as a result of the comparative analysis, only one of the same data within a predetermined time (pre-registered time) is recognized To control the operation of the bar opening with respect to the breaker.

4 is a flowchart illustrating a method of setting a map for photographing an image for roughness analysis according to an embodiment of the present invention.

In the present invention, two types of map setting are performed before photographing an image for roughness analysis. First, the resolution of the photographing unit is set according to the size of the road width. In step S416, the resolution width of the photographing unit is set such that the number of pixels in the photographing image range is at least 30 pixels, Set the map.

For this purpose, in step S414, the zoom range of the lens is set according to the resolutions of the photographing part in accordance with the map registered in advance such that the size of the license plate is set to 30 pixels or more for each resolution (41K, 80K, 1.3M, In the subsequent step S413, a scope map range for illuminance analysis is set for illuminance analysis around the number plate of the vehicle entering the incident photographing range. If the basic recognition range is confirmed in step S411, the recognition range of the partial illuminance of the front license plate and the rear license plate of the vehicle may be reset and changed in step S412.

When two or more maps are set before the image for roughness analysis is taken through the above process, if the vehicle enters the intrinsic photographing range, the peripheral illuminance of the license plate is analyzed in step S421_A and step S421_B, The blanks can be transformed into a well visible whole image. Therefore, even if light reflection, reflected light, backlight, or diffused reflection by vehicle light occurs, no recognition error occurs for the vehicle number. Also, if the car number is recognized from the front license plate, the car number can be recognized from the rear car license plate in the same way as recognizing the front license plate even if an error occurs due to damage, dirt or illegal painting.

5 is a flowchart illustrating a method of controlling opening and closing of a shutter based on an illuminance analysis value of an image according to an embodiment of the present invention.

When the illuminance analysis is performed on the front plate and the rear plate, the conventional photographing unit can not know at which position the current shutter is photographed or where the current shutter is located, Since the parameters affecting the recognition of the illuminance occur almost infinitely, the shutter value can only be changed little by little in comparison with the external illuminance. In addition, when the image quality is increased for the entire image to be photographed, the shadow image becomes darker and the partial image at the reflection point becomes darker or a Miller effect occurs.

In order to solve such a problem, in step S410 of FIG. 4, the basic data of two map settings preliminarily registered and the illuminance analysis in the selected range are used to photograph the image in which the current vehicle enters in step S510, Analyze illuminance and color around license plate and rear license plate.

In step S530, statistical values are calculated by integrally analyzing the current shutter position, maximum illumination, minimum illumination, image amplification value, and maximum shutter value, and as a result, the shutter value analyzed from the current shutter value If the shutter speed is smaller than the current shutter speed and the shutter speed is greater than the current shutter speed, the shutter is opened / closed by the difference in step S550 to move the shutter to the optimum shutter speed range.

In this case, a method has been described in which the front plate is recognized and the opening / closing of the shutter is controlled based on the illuminance analysis value of the image. However, when the front plate is not recognized, the same process as described above is performed to recognize the rear plate, .

6 is a flowchart illustrating a method for controlling a circuit breaker based on vehicle number information detected by a vehicle number recognizing apparatus and an RF reader according to an embodiment of the present invention.

When the car number recognizing apparatus 100 and the RFID device 200 are installed in the parking control facility and recognize the vehicle number, they recognize the entering vehicle at the same time, or recognize one device first and then recognize another device two times The same duplicate data is received in different types. Therefore, only once when the same data is received within a predetermined time, it should be recognized.

The recognized car number image is stored in the car number management server 300 in step S670 and the registered car number confirmation procedure for the RFID information of the entering car is requested to the car number management server 300 in step S640 do. If it is determined that the registered vehicle is the registered vehicle same as the vehicle number recognition data recognized by the vehicle number recognizing apparatus 100, only one of the same data within a predetermined time (pre-registered time) is recognized in order to prevent the breaker error, The operation of the heat can be controlled.

On the other hand, when the vehicle number recognizing apparatus 100 and the RFID apparatus 200 are installed in the parking control facility and recognize the vehicle number, the first-line operation data can be processed first.

For example, when the RFID information of the vehicle entering the intrusion shooting range is recognized, the vehicle number management server 300 is requested to check the registered vehicle number for the RFID information. As a result of the comparison analysis, If the number recognized by the number recognizing apparatus 100 is the same, then the tentative information recognized by the first device is firstly registered in the vehicle number management server 300 and the tentative information input from the subsequent device is ignored. At this time, the recognized image information is stored together with the entry information in step S670.

In the meantime, the car number recognition apparatus 100 can be installed in the vehicle control facility in connection with various fare calculators (an intermediate attraction rate calculator, an exit attraction fee calculator, an intermediate unmanned fare calculator, an exit unmanned fare calculator, and the like). When the request for the car number recognition data is received from the fare calculator, the car number recognition apparatus 100 can promptly distribute the image data to the charge calculator at the request of the car number management server 300. [

FIG. 7 is an exemplary view showing the reflected light, the photometric light, and the backlight depending on the position of the sun according to an embodiment of the present invention, and FIGS. 8 (A) and 8 (B) Fig. 10 is an example showing a range setting range for illuminance analysis in the entire photographing range screen of the rear part.

As described above with reference to Fig. 5, only the number plate moves the electronic shutter within the visible range based on the illuminance value within the selection range.

(IR) when the illuminance value within the readout result selection range is the daytime (HI section), and if the illuminance value within the range of the readout result is the daytime (HI section) Take a picture for analysis of the front part car number and a video for rear part car number analysis without turning on the lamp and the rear infrared (IR) lamp. If it is read at night, turn on the front infrared (IR) lamp and the rear infrared (IR) lamp, and then image the front panel car number analysis image and the rear panel car number image.

On the other hand, a polarizing film may be attached to the infrared ray pass filter to prevent image recognition errors caused by photometry (G-H section). In addition, the imaging device adopts a C-MOS device which does not cause smear phenomenon, thereby preventing the occurrence of a smear effect of light on the license plate when photometry occurs. The smear phenomenon means that a bright line appears in the vertical direction (or in the horizontal direction) when a bright light source is shot. In one embodiment, in the case where a C-MOS device or other material is used, in the case where smear and irregular reflection occur, a separate image correction algorithm may be used to reduce the occurrence of image recognition errors.

If the recognizable image is photographed with respect to the license plate, but the recognition of the car number fails, the recognized image data is deleted from the front surface of the car and the car number recognition process described in FIG. 3 is repeated. If the car number is not recognized despite repeated execution, the car number image data photographed at the rear portion is stored in the car number management server (300).

On the other hand, when the vehicle enters the recognition range, there is a backlit error caused by the vehicle body (shadow on the license plate), reflected light error (mirror phenomenon caused by the front surface of the vehicle), metering error (smear due to mirror- It is necessary to pre-register an area for analyzing the current illuminance around the license plate within the photographed image range. For this purpose, the vehicle number recognizing apparatus 100 may be installed at different places where the vehicle number recognizing apparatus 100 is installed, and a small vehicle to a large vehicle may be passed through to set a photographing distance and a range. And the range of illuminance recognition around the license plate for analyzing the area and the vehicle color is set in advance (see FIG. 8).

At this time, the lens zoom range of the photographing part is set and moved at a sufficient resolution to the width of the preliminary road, and the vehicle is stopped by the loop detector within the recognition range so that the road width can be sufficiently covered. Is registered so that the recognition rate of at least 30 pixels is more than the confirmation value of the basic recognition range per resolution.

4, the resolution of the photographing unit is set according to the size of the road width, the resolution road width map is set for the photographing unit so that the license plate recognition rate per resolution of the photographing unit becomes the maximum, An image for vehicle front surface illuminance analysis is taken based on the loop detection signal generated by the front surface loop detector, and the lamps within the predetermined selection range and vehicle color are analyzed to calculate the illuminance value within the selected range.

The controller 100 also analyzes the shutter position, the maximum and minimum illuminance, the image amplification value, and the maximum shutter value of the front and rear photographing units 110 and 120 based on the calculated illuminance values, And controls the operation of the shutter of the photographing section by the difference value when the shutter value analyzed is smaller than the shutter value at the shooting time. For example, if the shutter value is greater than the analytical shutter value, the shutter is opened. If the analysis shutter value is larger than the current shutter value, the shutter is closed by the difference, To the shutter range of the shutter.

According to the present invention, there is provided an apparatus for recognizing a vehicle number, a method for identifying the same, and a computer-readable recording medium on which a program for performing the method is recorded, Can be photographed, and the vehicle number can be stably read out from the photographed image.

In addition, even when metering or headlight diffuse reflection occurs, images without smear phenomenon and Miller phenomenon can be taken and the vehicle number can be reliably read.

In addition, if the vehicle license plate is blocked due to snow or rain due to natural phenomena, if the license plate is struck on the license plate while driving on the road, the license plate of the vehicle is illegally modified or illegally painted, The vehicle number can be recognized effectively even if it can not be recognized.

An embodiment of a car number identification method according to an aspect of the present invention is implemented by a program command and is executed in a computing unit readable recording medium. The computing unit readable recording medium may include a program command, a data file, a data structure, or the like, alone or in combination. The computing unit readable recording medium may be a magnetic disk such as a hard disk, a floppy disk, Optical media such as optical media such as CD-ROM and DVD, magneto-optical media such as Floptical Disk, and optical disks such as ROM, RAM, Memory devices, and the like, which are specifically configured to store and execute program instructions. The program instructions may be those specially designed and configured for the present invention or may be available to those skilled in the computing software arts. Program instructions include machine language code such as those generated by the compiler, as well as high-level language code that can be executed by the computing unit using an interpreter or the like.

The method of the present invention described above is not limited to the order of each of the illustrated steps. That is, the order of each step may vary according to the technical level of a person skilled in the art, and a plurality of steps may occur at the same time. Those skilled in the art will recognize that the steps illustrated are not exclusive and that one or more other steps may be included in a particular step and that certain steps described in the flowchart may be omitted to the extent that they do not affect the technical scope of the present invention.

The above-described embodiments of the present invention include examples of various aspects as long as they fall within the scope of the claims. Accordingly, it should be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

100: car number recognition device 110: front photographing part
112, 122: image sensor 113, 123: CPU
114, 124: Communication control unit 170: Power supply unit
115: front infrared pass filter 125: rear infrared pass filter
150: control unit (DIO board) 160: computing unit
161: illuminance analysis unit 162: shutter control unit
163: car number recognizing unit 120: rear photographing unit
114, 124: communication control unit 113, 123: CPU
111: front lens 121: rear lens
130: front infrared lamp 140: rear infrared lamp

Claims (10)

At least one photographing section for photographing an image of an incoming vehicle on the basis of a loop detection signal within an incident photographing range;
An illuminance analyzer for analyzing an area where a license plate is located and a vehicle color with respect to the photographed image and calculating an illuminance value within a selected range;
A shutter control unit for controlling the shutter operation of the photographing unit based on the calculated illuminance value and capturing an image for recognizing the vehicle number; And
A car number recognizing unit for recognizing the car number of the incoming car by reading the photographed car number recognition image;
And the vehicle identification number. The method according to claim 1,
Wherein the illuminance analyzing unit sets an illuminance recognition range around the license plate for analyzing the area where the license plate is located and the color of the vehicle in the photographed image. The method according to claim 1,
The image of the entering vehicle and the image of recognizing the car number are photographed at the front and rear portions of the vehicle,
Wherein the car number recognizing unit recognizes the car number from the car number recognition image photographed at the rear side of the vehicle when the car number is not recognized from the car number recognition image. The method according to claim 1,
The shutter control unit analyzes the shutter position, the maximum and minimum illuminance, the image amplification value, and the maximum shutter value of the photographing unit based on the calculated illuminance value, and determines whether the analyzed shutter value is smaller than the shutter value at the photographing time, And controls the opening / closing of the shutter of the photographing section by the difference value when the shutter value analyzed is larger than the shutter value. (A) setting an illuminance recognition range around the license plate for analyzing the area where the license plate is located and the vehicle color in the photographed image;
(B) photographing an image for illuminance analysis based on a loop detection signal within an incident range when the vehicle enters the vehicle;
(C) calculating an illuminance value within a selected range by analyzing an area where the set number plate is located and a vehicle color;
(D) photographing an image for vehicle number recognition by controlling the shutter operation of the photographing section in the recognition range of the license plate based on the calculated illuminance value; And
(E) reading the photographed vehicle number recognition image to recognize the vehicle number of the entry vehicle;
And the vehicle identification number. 6. The method of claim 5,
And controlling ON / OFF of the infrared lamp based on the illuminance value in the selection range when photographing the illuminance analysis image. 6. The method of claim 5,
And recognizing the vehicle number from the vehicle number recognition image photographed at the rear side of the vehicle when the vehicle number is not recognized from the vehicle number recognition image photographed at the front surface of the vehicle. 6. The method of claim 5,
Recognizing RFID CARD information from an entry vehicle;
Requesting a registration inquiry to the car number management server for the recognized RFID CARD information; And
Recognizing the car number recognition image and the recognized car number among the car numbers recognized through the registration inquiry as the number of the entering car when the inquiry result is the same car number as the car number recognized from the car number recognition image, ;
And the vehicle identification number. 6. The method of claim 5,
If the vehicle number is not recognized from the vehicle number recognition image photographed at the front portion of the vehicle or the vehicle number recognition image photographed at the rear portion of the vehicle, the image for recognizing the vehicle number photographed at the front portion of the vehicle is deleted, And analyzing and storing the image for car number identification. A computer-readable recording medium recording a program for performing the method of any one of claims 5 to 9.

Images