KR101407322B1 - The Car Number Recognizing System Using Motion Recognition Based On Macro Block - Google Patents

Abstract

The present invention relates to a number recognizing system which can detect a vehicle and recognize vehicle number by estimating a motion vector of an object photographed by a camera, thereby efficiently detecting the vehicle number, and a number recognizing method thereof. The vehicle recognizing system according to an embodiment of the present invention includes a camera for photographing a first image related to a plurality of objects, a memory for storing motion vector information on a vehicle among the plurality of objects, and a controller for estimating first motion vectors of the plurality of objects from motions of the plurality of objects. The controller detects a change in brightness of two arbitrary continuous images constituting the first image induced due to the motions of the plurality of objects, estimates the first motion vector using the detected brightness change, and compares the first movement vector with the stored motion vector information to recognize the vehicle among the plurality of objects.

Description

[0001] The present invention relates to a number recognition system using macroblock-based motion recognition,

[0001] The present invention relates to a number recognition system and a recognition method for recognizing a vehicle number by detecting a vehicle on the roadway, and more particularly, to a method of detecting a brightness change between two consecutive images constituting a detection image, It is based on Lucas-Kanade Optical flow that estimates motion vector based on brightness change. It is a number recognition system that can detect the car number efficiently by detecting the car in the image taken by the detector camera and recognizing the number. And a recognition method.

Parking on the Road Traffic Law means that the driver waits for a passenger, carries a cargo, the car breaks down or keeps the vehicle stopped for any other reason, or leaves the driver unable to drive the vehicle immediately after leaving the vehicle .

In addition, a stop means that the driver stops the vehicle without exceeding five minutes and refers to a stop state other than the parking.

Generally, it is easy to park the vehicle on both sides (or the shoulder) of the road. Since the vehicles that have been parked in this way can obstruct the flow of other vehicles in operation and actually narrow the width of roads and cause traffic accidents, the Road Traffic Act prohibits illegal parking cars by setting up various prohibition signs.

However, it is a fact that the police force who controls the police can not be deployed in every parking monitoring area.

In order to overcome this situation, the traffic police are enforcing the speedy enforcement, but the effect is temporary, the cost of the intervention manpower can be increased, and there is a problem of conflict or friction with the civilian person during enforcement.

Therefore, it is widely used to control unlawful parking vehicles by installing unmanned surveillance cameras in the restricted area. The method of interception by the unmanned surveillance camera can be performed by a method of detecting the presence or absence of an illegally parked vehicle by installing a surveillance camera on the prohibited area.

The conventional method of intermittently driving an illegally parked vehicle using a surveillance camera includes the steps of determining whether an illegal parking vehicle is present in each channel of the prohibited area by using a detection camera and detecting the presence of the illegally parked vehicle by using an intermittent camera capable of performing pan, The vehicle was controlled in a manner that was interrupted.

However, when photographing an illegal parking area using a detection camera to photograph whether or not an illegally parked car exists, there is a problem in that frequent erroneous detection that detects objects other than the vehicle existing on the road or the street occurs there was.

In addition, a large number of objects such as rear cars, motorcycles, bikes, shadows, manholes, various characters on roads, crosswalks, etc. are actually present in the vicinity of the detection area other than the vehicle to be detected by the detection camera. There is a problem that the time required for detecting the vehicle may be delayed.

In addition, the conventional number recognition system has a problem in that it perceives numbers per frame, resulting in recognition results proportional to computer performance.

Therefore, there is a need for development of a vehicle identification system capable of performing efficient detection by preventing mis-detection, increasing the intermittent rate, and minimizing the recognition result according to computer performance.

Patent No. 10-0785757 Patent No. 10-0834550 Patent No. 10-0502980

Disclosure of Invention Technical Problem [8] The present invention has been made to solve the above-mentioned problems, and it is an object of the present invention to provide a method and apparatus for detecting a brightness change between two consecutive images constituting a detection image and estimating a motion vector based on the detected brightness change The object of the present invention is to provide a user of a number recognition system and a number recognition method using LK Optical Flow (Lucas-Kanade optical flow) based motion estimation technology.

Specifically, there is provided a vehicle recognition system and a vehicle recognition method for recognizing a vehicle in a video shot by a detection camera using a number recognition system, a number recognition system for recognizing a vehicle number, and a number recognition method, have.

It is another object of the present invention to provide a vehicle recognition system and a vehicle recognition method for reducing an error rate by detecting only a vehicle by comparing an image photographed by a detection camera with stored motion vector information.

It is also an object of the present invention to provide a user with a number recognition system and an intermittent method capable of performing intermittent processing by enlarging a detection image even on an illegally parked vehicle remote from a detection camera to perform vehicle recognition.

Another object of the present invention is to provide a user with a number recognition system and a control method capable of performing vehicle recognition by distinguishing a vehicle that has been parked outside the vehicle within the detection area from other objects.

It is to be understood that both the foregoing general description and the following detailed description of the present invention are exemplary and explanatory and are not intended to limit the invention to the precise form disclosed. It can be understood.

A vehicle recognition system according to an embodiment of the present invention for realizing the above-mentioned object includes a camera for photographing a first image related to a plurality of objects, a memory for storing motion vector information for the vehicle among the plurality of objects, And a controller for estimating a first motion vector of each of the plurality of objects based on the motion of the plurality of objects, The method of claim 1, further comprising: detecting a change in brightness between images; estimating the first motion vector using the detected brightness change; comparing the first motion vector with the stored motion vector information to recognize the vehicle have.

In addition, the controller may use the LK optical flow (Lucas-Kanade Optical Flow) technique.

The stored motion vector information may be for a plurality of vehicle images having different sizes.

In addition, the control unit may control the memory to additionally store the first motion vector information for the vehicle.

The controller divides the first image into macroblocks having the same size, and when the motion value, which is an absolute value of the first motion vector of the first macroblock that is at least a part of the divided macroblocks, is 1/4 or more , Dividing the first macroblock into N * M sub-macroblocks, and setting a motion vector of a second macroblock having the largest motion value among the divided second macroblocks as a motion vector of the first macroblock have.

In addition, the controller may consider that there is no motion when the motion value, which is an absolute value of the first motion vector of the first macroblock, is less than 1/4.

In addition, the control unit can recognize the text of the license plate of the recognized vehicle.

Meanwhile, a vehicle recognition method related to an example of the present invention for realizing the above-mentioned problem includes a first step of shooting a first image related to a plurality of objects, a first step of acquiring a first motion of each of the plurality of objects A second step of estimating a motion vector, a third step of recognizing a vehicle among the plurality of objects by comparing the first motion vector and motion vector information, The method includes detecting a change in brightness between two consecutive images constituting the first image induced by a motion and estimating the first motion vector using the detected brightness change, And may include motion vector information for the motion vector.

Also, the second step may utilize the LK optical flow (Lucas-Kanade Optical Flow) technique.

In addition, the motion vector information may be for a plurality of vehicles having different sizes.

The method may further include storing the first motion vector information for the vehicle in a memory for storing motion vector information for the vehicle among the plurality of objects.

The method may further include the steps of: dividing an image into macroblocks having the same size between the third step and the fourth step; dividing the motion value, which is an absolute value of the first motion vector of the first macroblock, Dividing the first macroblock into N * M sub-macroblocks, and dividing the motion vector of the second macroblock having the largest motion value among the divided second macroblocks into the first macroblock, As a motion vector of the block.

If the motion value of the first macroblock is less than 1/4 of the absolute value of the motion vector of the first macroblock, it may be considered that there is no motion.

The method may further include recognizing the text of the license plate of the recognized vehicle.

The present invention applies a LK Optical Flow (motion flow) based motion estimation technique to calculate and extract a feature vector to recognize a vehicle in an image captured by a detection camera, It is possible to provide the user with the emergency interception system and the intermission method.

Specifically, by applying the LK Optical Flow-based motion estimation technique, feature vectors are extracted and compared with the built-in learning data of the images taken by the detection camera, and by detecting only the illegally parked vehicles, the detection rate is reduced It is possible to provide the user with an illegal parking intermittent system and an intermittent method that increase the intermittent rate.

In addition, it is also possible to provide an illegal parking intermittent control system and an intermittent control method capable of performing intermittent processing by enlarging a detection image even on an illegally parked vehicle remote from the detection camera to perform vehicle recognition.

In addition, the illegally parked intermittent intermittent system and the intermittent vehicle control method capable of distinguishing a vehicle that has been parked outside the vehicle within the detection area from other objects and performing vehicle recognition can be provided to the user.

In addition, by recognizing a vehicle by distinguishing it from other objects, it is possible to solve a misidentification part due to an object (a banner, etc.) similar to a vehicle number in the surrounding environment, and unnecessary calculation is not required, thereby reducing the recognition result difference depending on the computer performance.

It should be understood, however, that the effects obtained by the present invention are not limited to the above-mentioned effects, and other effects not mentioned may be clearly understood by those skilled in the art to which the present invention belongs It will be possible.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate a preferred embodiment of the invention and, together with the description, serve to provide a further understanding of the technical idea of the invention, It should not be construed as limited.
1 shows an example of a block diagram of a number recognition system that can be applied to the present invention.
Fig. 2 shows an example of a block diagram of a control section that can be applied to the present invention.
3A and 3B are a plan view and a side view of a structure in which a number recognition system is associated with an example of the present invention.
4 is a flowchart illustrating a method of recognizing numbers according to an example of the present invention.
5 shows an example of estimating a motion vector in a macroblock unit according to the present invention.
6A and 6B show an example of recognizing a vehicle by estimating a motion vector that can be applied to the present invention.

In the past, police officers directly controlled vehicles that were illegally parked on both sides of the road. However, a method is currently used in which a man-in-the-middle can not be deployed in any prohibited area, and an unmanned surveillance camera is installed.

However, when photographing a prohibited area by using a detection camera, there is a problem that frequent occurrence of an erroneous detection that detects objects other than a vehicle existing on the road or a distance may occur.

In addition, there are problems in that a lot of objects such as a banner or the like other than the vehicle to be detected by the detection camera actually exist in the vicinity of the detection area, and the time required for detecting the vehicle may be delayed.

In addition, the conventional number recognition system has a problem in that it perceives numbers per frame, resulting in recognition results proportional to computer performance.

Accordingly, in the present invention, a number recognition system capable of increasing the number recognition efficiency by applying the LK Optical Flow (LK optical flow) method to an image taken by a detection camera is proposed.

Hereinafter, a preferred embodiment of the present invention will be described with reference to the drawings. On the other hand, an embodiment described below does not unduly limit the contents of the present invention described in the claims, and the entire structure described in this embodiment can not be said to be essential as the solution means of the present invention.

Hereinafter, the number recognition system proposed by the present invention will be described in detail.

1 shows an example of a block diagram of a number recognition system that can be applied to the present invention.

1, the number recognition system 10 includes a camera module 100, an output unit 200, a communication unit 300, a memory 400, an interface unit 500, a power supply unit 600, a control unit 700, And the like.

However, the components shown in FIG. 1 are not essential, so that a number recognition system having components with fewer or fewer components may be implemented.

Hereinafter, the components will be described in order.

First, the camera module 100 processes an image frame such as a still image or a moving image obtained by photographing a road. The image frame processed by the camera module 100 may be stored in the memory 400 or may be transmitted to the outside through the communication unit 300. The processed image frame may be displayed on the display unit 210. [

At this time, two or more cameras used in the camera module 100 may be provided, depending on the use environment.

For example, the camera module 100 may include a detection camera 110, an intermittent camera 120, and the like. However, the present invention is not limited to such a configuration, and may include a configuration including other shooting means.

On the other hand, the detection camera 110 photographs the prohibited area and can detect whether or not the vehicle enters the prohibited area using the sensed image.

The detection camera 110 may be implemented using a camera equipped with a fisheye lens. In the case of using a fisheye lens having a wide angle of view, it is possible to take an image of an omnidirectional (360) region around the detection camera 110 and utilize it as a detection image.

However, since the specific point of the road can not be enlarged even if the detection camera 110 is installed, an intermittent camera 120 capable of performing a pan, tilt, and zoom operation is needed.

The intermittent camera 120 may perform at least one of a pan operation, a tilt operation, and a zoom operation to photograph a license plate of a vehicle illegally parked in the prohibited area. The intermittent camera 120 may preferably use an LPR (License Plate Recognition) camera.

The LPR camera is provided with a tilting device capable of tilting in the x-axis, the y-axis and the z-axis direction, respectively. Such a configuration is easy for those having ordinary skill in the art to which the present invention belongs. . Such an LPR camera has a configuration capable of photographing a zoom-in image or a zoom-out image with respect to the vehicle by rotating the camera at designated x, y coordinates.

Meanwhile, the output unit 200 generates an output related to a visual or auditory sense, and may include a display unit 210, a warning unit 220, and the like.

The display unit 210 may display (output) information processed in the number recognition system 10. [ For example, a UI (User Interface) or a GUI (Graphic User Interface) associated with the number recognition system 10 is displayed. A still image or moving image photographed by the camera module 100, a video image transmitted / received through the communication unit 300, a UI, a GUI, and the like.

Also, the display unit 210 may be used as an illumination light for interrupting the crime prevention area when the number recognition system 10 is used for crime prevention at night or in a dark space.

The display unit 210 may be a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT LCD), an organic light-emitting diode (OLED) A flexible display, and a three-dimensional display (3D display).

The warning unit 220 outputs a signal for notifying the occurrence of the event of the number recognition system 10. An example of an event generated in the number recognition system 10 is an illegal driving vehicle of a vehicle in a prohibited driving area.

The warning unit 220 may output a form other than an audio signal or a video signal, for example, a warning notice document. In this case, a printer for outputting a warning notice document may be connected.

The video signal may be output through the display unit 210. In this case, the display unit 210 may be classified as a kind of the warning unit 220. [

Meanwhile, the communication unit 300 includes one or more modules that enable communication between the number recognition system 10 and the wire / wireless communication system or between the number recognition system 10 and the network in which the number recognition system 10 is located . For example, the communication unit 300 may include a wired / wireless Internet module 310, a short distance communication module 320, a location information module 330, and the like.

The wired / wireless Internet module 310 refers to a module for wired / wireless Internet access, and may be built in or enclosed in an illegal parking system.

WLAN (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), WCDMA (Wideband Code Division Multiple Access), HSDPA (High Speed Downlink Packet Access) , LTE (Long Term Evolution), or the like can be used.

The short-range communication module 320 is a module for short-range communication. Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and the like can be used as the technique of the short range communication.

The position information module 330 is a module for obtaining the position of the number recognition system 10, and a representative example thereof is a Global Position System (GPS) module. According to the current technology, the GPS module calculates distance information and accurate time information from three or more satellites, and then applies trigonometry to the calculated information to obtain three-dimensional current position information according to latitude, longitude, and altitude It can be calculated accurately. At present, a method of calculating position and time information using three satellites and correcting an error of the calculated position and time information using another satellite is widely used. In addition, the GPS module can calculate speed information by continuously calculating the current position in real time.

Meanwhile, the memory 400 may store a program for processing and controlling the control unit 700, and may store a program for temporarily storing input / output data (e.g., motion vector information of a still image, Function may be performed. The frequency of use of each of the data (for example, frequency of use for each motion vector information) may also be stored in the memory 400.

The memory 400 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory, etc.) ), A random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read- A magnetic disk, an optical disk, a memory, a magnetic disk, or an optical disk. The number recognition system 10 may operate in association with a web storage that performs the storage function of the memory 400 on the Internet.

Meanwhile, the interface unit 500 serves as a pathway to all the external devices connected to the number recognition system 10. The interface unit 500 receives data from an external device or supplies power to each component in the number recognition system 10 or allows data in the number recognition system 10 to be transmitted to an external device.

For example, a port for connecting an image or an image photographed by the camera module 100 to an external device, an external charger port, a wired / wireless data port, a memory card port, An audio I / O port, a video I / O port, and the like may be included in the interface unit 500.

Meanwhile, the power supply unit 600 receives external power and internal power under the control of the controller 700, and supplies power required for operation of the respective components.

On the other hand, the controller 700 typically controls the overall operation of the number recognition system 10. For example, related control and processing are performed for video shooting, detection of illegally parked vehicle, and creation of intervention data.

For example, the control unit 700 receives the image photographed by the detection camera 110, and can determine whether to intercept the vehicle when the vehicle is parked in the prohibited area. In addition, when the illuminance of the diaphragm-prohibited area is not uniform, the control unit 700 detects the illuminance and adjusts the light intensity of the display unit 210 toward the bright area to be weak and adjusts the light intensity of the display unit 210 Can be strongly controlled.

The various embodiments described herein may be implemented in a recording medium readable by a computer or similar device using, for example, software, hardware, or a combination thereof.

According to a hardware implementation, the embodiments described herein may be implemented as application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays May be implemented using at least one of a processor, controllers, micro-controllers, microprocessors, and other electronic units for performing other functions. In some cases, The embodiments described may be implemented by the control unit 700 itself.

According to a software implementation, embodiments such as the procedures and functions described herein may be implemented in separate software modules. Each of the software modules may perform one or more of the functions and operations described herein. Software code may be implemented in a software application written in a suitable programming language. The software code is stored in the memory 400 and can be executed by the control unit 700. [

2 shows an example of a block diagram of a control unit 700 that can be applied to the present invention.

2, the control unit 700, which may be applied to an example of the invention, includes a motion recognition unit 710, a vehicle recognition unit 720, an illegal parking distance determination unit 730, a license plate recognition unit 740, Means 750, camera control means 760, memory control means 770, and the like.

However, the configuration of the controller 700 is not limited thereto, and it is possible to implement the configuration with more or fewer components.

First, the motion recognition unit 710 receives the detection image of the prohibited area for the pseudo-range captured by the detection camera 110, and recognizes the motion using the LK Optical flow (LK optical flow) technique. Hereinafter, the LK optical flow will be described in detail.

Optical flow

When a camera is used to obtain a temporally continuous image, when the position of the camera is moved relative to the object or the position of the object is moved relative to the camera, the brightness of each pixel in the image is changed. Is called optical flow.

The basic assumption of optical flow is that for every pixel between two images, the intensity does not change for a very short time, but only the position changes. If a position change occurs during time t, this change is judged by motion.

If there is movement between two images, the intensity value at the x, y coordinates in the current image will appear at the position shifted by? X and? Y in the image after t time, and can be expressed as Equation 1 below .

If the Taylor series is applied to Equation (1), Equation (2) can be obtained.

는 (x,y,t)에 있는 영상에서 각 방향에 해당하는 미분 성분이며,

는 수학식 3으로 유도될 수 있다.Here, Vx and Vy are the x and y velocities of I (x, y, t). Also

Is a differential component corresponding to each direction in the image at (x, y, t)

Can be derived by Equation (3).

Lucas-Kanade Optical flow (LK flow)

An easy way to find motion vectors for each part is LK Optical flow.

This is to set a block centered on the point at each point in the image and estimate the motion vector by applying a low formula in the block unit.

In the present invention, it is based on Luclas-Kanade (LK) Optical Flow, which is a space-time gradient method capable of obtaining motion of an entire image to track an arbitrary point in an image. The LK method assumes the following.

1. Brightness constancy: A pixel on an object does not change its value even if the frame changes. In the case of brightness images, it is assumed that the brightness of the object pixel being tracked does not change.

2. Temporal persistence: Motion is not so fast in the image. In other words, the change of the time is faster than the movement of the object in the image, which means that the amount of movement of the object between consecutive frames is not large.

3. Spatial coherence: Spatially adjacent pixels are likely to belong to the same object and have the same motion.

Motion estimation based on LK Optical Flow is divided into two stages.

)를 추출한다.(1) Gradient Extraction: Using the second derivative (x, y)

).

(2) Optical Flow Calculation: Basically, if there is very little change in brightness between two adjacent images, the movement point can be found around the point of interest and the motion vector (dx, dy) can be approximated.

(Middle omitted)

는 관심 지점의 주변의 화소들(

) 이며

는 현재 t에서의 주변 픽셀의 부분 미분 값이다. 위의 항등식을 행렬 형태로 표현하면

이며 다음의 수학식 5와 같다.In Equation 4,

The pixels around the point of interest

) And

Is the partial derivative of the surrounding pixels at t. If we express the above equation in matrix form

And is expressed by the following equation (5).

)의 해를 구하면 다음의 수학식 6과 같다.Using the least squares principle (2x2) method,

), The following equation (6) is obtained.

The motion vectors Vx and Vy can be obtained by the above method.

If the motion value in the macroblock is 1/4 or more, the motion recognizing unit 710 determines the macroblock as a real motion with motion and divides the macroblock into N * M sub-blocks. The motion vector of the sub-block having the largest motion value among the divided sub-blocks is allocated as a motion vector of the corresponding macroblock.

This is to remove noise, such as shadows and noise, rather than actual vehicle motion.

FIG. 3 is a flow chart illustrating a process of recognizing the vehicle by the motion recognition unit 710. FIG. 3 shows a process of recognizing motion using LK optical flow that can be applied to the present invention.

Object is a picture in which the object part of the image is divided into macroblocks using LK optical flow. In this figure, the white part is the part in which the motion exists in the image, and the box selected in red (Selected Motion Box) is a sub-block judged to be a real motion having a motion value of 1/4 or more.

In FIG. 3, the middle picture is an enlarged view of one macroblock. In the upper left block, the motion value is less than 1/4, and it is judged that there is no motion, so that the motion is selected as zero motion Part is a case where the motion value is 1/4 or more and corresponds to a real motion.

Meanwhile, the vehicle recognition unit 720 receives the motion vector estimated by the motion recognition unit 710 and compares the motion vector with the motion vector information stored in the memory 400 to recognize the vehicle.

On the other hand, the illegal parking discrimination means 730 can judge whether or not the vehicle has been parked on the parking prohibited area.

That is, when the vehicle recognizing means 720 receives the motion vector analyzed by the motion recognizing means 710 and recognizes the vehicle in the prohibited area, the illegal parking discrimination means 730 judges whether the vehicle is illegally parked It can be determined whether or not the intermittent process is to be performed.

It can not be concluded that the vehicle was illegally parked only on the basis of the recognition of the vehicle on the detection image, and it can be said that the vehicle was illegally parked only when the vehicle stopped in the prohibited parking area for a predetermined period of time.

Accordingly, the illegal parking differential determination means 730 can determine whether the vehicle is illegally parked by using the detection image photographed at predetermined intervals of time.

That is, when the illegal parking distance determination unit 730 recognizes the presence of the vehicle in the parking space prohibited area at the beginning, the detection camera 110 controls the parking area to again photograph the parking space prohibited area after a predetermined time has elapsed. For this, the camera control means 760 can control the operation of the detection camera 110 at the same time.

After the lapse of the preset time, the motion recognition means 710 re-estimates the motion vector, and the vehicle recognition means 720 receives the motion vector estimated by the motion recognition means 710. [

The motion vector thus received is compared with the motion vector stored in the memory 400. The vehicle recognition unit 720 can determine whether there is a vehicle among the objects photographed on the detection image photographed after a predetermined time elapses, Can be recognized.

When the illegal parking distance determining means 730 determines that the vehicle recognized in the detection image after the lapse of the preset time is the same as the recognized vehicle in the initial detection image, the vehicle is regarded as having made illegal parking.

On the other hand, when it is judged that the vehicle recognized in the detection image after the lapse of the predetermined time and the vehicle recognized in the initial detection image are not the same, the vehicle is recognized as having not illegally parked the vehicle, Photograph the prohibited area and search for entry of the vehicle.

On the other hand, the license plate recognizing means 740 can recognize the characters of the license plate of the illegally parked car by receiving the image photographed by the intermittent camera 120.

For character recognition, one of the three detection methods of the license plate position can be executed first.

First, the feature region of the license plate is detected using the vertical and horizontal edge information from the photographed image.

The second is to detect the position of the license plate by the scan data analysis.

The third is to detect the exact license plates by directly searching for numbers and letters.

When the position of the license plate is detected, the recognition algorithm uses the numbers, letters (consonants, vowels, and vowels) to recognize the characters by template matching (Hangul consonant + number) ) Are classified in detail and the recognized characters are re-confirmed, thereby minimizing the error in decoding the characters.

On the other hand, the filtering unit 750 can determine whether or not to exclude from the object of interception by considering the size of the vehicle on the detected image.

In the case of photographing the detection image for the prohibited area using the detection camera 110, the size of the vehicle photographed on the photographed detection image varies depending on the distance from the detection camera 110 to the actual vehicle position.

That is, since the lower end portion of the detection image is a space near the support where the number recognition system 10 is installed, if the actual vehicle is located near the detection camera 110, the vehicle captured on the detection image is positioned at the lower end portion of the detection image And the size of the vehicle on the detection image will be large.

On the other hand, if the actual vehicle is located far from the detection camera 110, the vehicle captured on the detection image will be positioned at the upper part of the detection image, and the size of the vehicle captured on the detection image will be smaller.

In this way, the filtering means 750 can calculate the distance from the detection camera 110 to the actual vehicle position by using the position of the detected image of the vehicle recognized by the vehicle recognition means 720. [

In addition, the filtering unit 750 can calculate the estimated size of the vehicle image on the detected image using the calculated distance, and the size of the vehicle image on the detected image is much different from the estimated size of the vehicle image It is possible to prevent misjudgment by excluding it from the object of interception.

That is, it is calculated that the vehicle recognized by the vehicle recognition means 720 is located at the lower end portion of the detection image and is located close to the detection camera 110. If the size of the vehicle image on the detection image is small, The vehicle is not actually a vehicle and is likely to be an error, so it can be excluded from the control.

On the other hand, if it is determined that the vehicle recognized by the vehicle recognizing means 720 is located on the upper part of the detection image and is located far from the detection camera 110, if the size of the vehicle image on the detection image is large, The vehicle is not actually a vehicle but is likely to be an error, so it can also be excluded from the control.

Meanwhile, the camera control unit 760 can control the overall operation of the detection camera 110 and the intermittent camera 120 belonging to the camera module 100.

The camera control means 760 may control the number recognition system 10 to photograph the detection image of the road using the detection camera 110 so as to control the vehicle stopping in the prohibited area.

In addition, the camera control means 760 can control to shoot a detection image for the forbidden zone again after a predetermined time so as to judge whether or not the vehicle stopped in the prohibited area has been parked on the prohibited area have. This can be controlled together with the illegal parking discrimination means 730.

The camera control means 760 receives the positional information of the stopped vehicle determined by the vehicle recognition means 720 and can photograph the license plate of the vehicle stopped by the intermittent camera 120 in the prohibited area Tilt, and zoom operations of the intermittent camera 120 so that the intermittent camera 120 may be controlled by the intermittent operation.

On the other hand, the memory control means 770 can control the overall operation of various data input to / output from the memory 400. [

The vehicle recognition unit 720 of the control unit 700 extracts a motion vector from the detected image and compares the extracted motion vector with motion vector information of a general vehicle image of the memory 400. [

To this end, the memory control means 770 can control the memory 400 to output motion vector information for a general vehicle image to the vehicle recognition means 720. [

If the motion vector information for the vehicle recognized by the vehicle recognition means 720 and / or the filtering means 750 does not exist in the motion vector information of the memory 400, it is compared with the next motion vector information The motion vector information may be stored in the memory 400 for use.

To this end, the memory control means 770 may control the motion vector information for the vehicle recognized by the vehicle recognition means 720 and / or the filtering means 750 to be input to the memory 400.

Hereinafter, an installation structure of the number recognition system having the above-described configuration will be described with reference to the drawings.

4A and 4B are a top view and a side view of a structure in which an illegal parking intermittent system related to an example of the present invention is installed.

4A and 4B, the illegal parking system structure of the present invention may include a support 12, a crossbar 14, a detection camera 110, an intermittent camera 120, and the like.

However, the components shown in FIGS. 4A and 4B are not essential, so that a number recognition system having components with fewer components or fewer components may be constructed. Hereinafter, the installation structure of FIGS. 4A and 4B will be described.

It is preferable that the column 12 is fixedly installed on the ground within the prohibited area or near the ground, and is fixed to the ground by a bolt or inserted and fixed in the ground. The post 12 can be installed at a sufficient height to allow the intermittent camera 120 to take a wide area.

The support 12 may be formed hollow so that electric wires connected to the detector camera 110, the intermittent camera 120, the output unit 200, the communication unit 300, And the material thereof is preferably made of a metal material which is not corroded by rainwater or the like.

At least one cross bar 14 may be connected to the upper part of the column 12 and the inside of the column 12 may be hollow as in the case of the column 12, .

The crossbar 14 may be positioned horizontally with the ground, preferably above the anti-vehicular zone.

The detection camera 110 and the intermittent camera 120 can process an image such as a still image or a moving image obtained by photographing the prohibited area. The detection camera 110 and the intermittent camera 120 may be installed at the end of the crossbar 14, and preferably disposed on a prohibited area for intermission.

As shown in FIG. 3A, in the illegal parking intermittent system in which the illegal parking regulation system is installed, there may be a vehicle 21 parked near the detection camera 110 and a vehicle 22 parked away from the detection camera 110 have.

As described above, when the detection camera 110 is used to photograph a detection image for a pseudo range-prohibited area, the vehicle 21 that has been parked near the detection camera 110 is positioned at the lower end of the detection image.

Therefore, the filtering unit 740 can calculate the distance from the detection camera 110 to the vehicle 21 using the position of the vehicle on the detection image.

The distance between the detection camera 110 and the vehicle 22 can be calculated from the top of the detection image.

Hereinafter, the number recognition method of the number recognition system will be described with reference to FIG.

Referring to FIG. 5, first, the detection camera 110 captures a detection image of a road (S1010).

Then, the motion recognition unit 710 receives the first detection image captured by the detection camera 110, and estimates a motion vector for the detection image using the LK optical flow (S1020).

Subsequently, the motion recognizing means 710 divides the detected image into macroblocks having the same size, and calculates the motion values of the respective macroblocks (S1030)

Then, the motion recognition unit 710 determines whether the motion value of each macroblock is 1/4 or more (S1040)

Subsequently, the motion recognizing means 710 subdivides N * M macroblocks only for macroblocks having a motion value of 1/4 or more (S1050)

Then, the motion recognition unit 710 assigns the motion vector of the lower macroblock having the largest motion value among the lower macroblocks to the motion vector of the upper macroblock (S1060).

Then, the vehicle recognition unit 720 receives the motion information estimated and analyzed by the motion recognition unit 710 and compares the motion vector information stored in the memory 400 to recognize the vehicle among the objects photographed in the detected image (S1070 ).

The motion vector information stored in the memory 400 includes motion vector information for various kinds of vehicle images. Since the vehicle image has various sizes, the vehicle can be recognized regardless of the size of an object recorded on the first detection image It is possible.

In step S1070, the motion vector information may be selected and compared with the first motion vectors to perform faster vehicle recognition.

It is possible to select only the motion vector information for the vehicle image within the calculated image size range and compare the selected motion vector information with the motion vectors.

According to the recognition process, an object to be compared with the motion vector information can be reduced, the amount of calculation is greatly reduced, and rapid vehicle recognition can be performed.

Subsequently, the vehicle recognizing means 720 can judge whether the vehicle is recognized in the detected image (S1080)

Then, the license plate recognizing means 740 recognizes the number from the license plate of the recognized car (S1090)

Then, the memory control means 770 adds the motion vector information for the interrupted vehicle to the motion vector information of the memory 400 (S1100), and the added data can be used for comparison with the motion vector information at the next interruption The recognition rate can be improved.

Hereinafter, an example in which the vehicle is recognized from the detection image using the macroblock-based motion recognition of the present invention will be described with reference to FIGS. 6A and 6B.

FIG. 6A is the 2000 th frame of the embodiment, and FIG. 6B is the 2450 th frame of the embodiment. In FIG. 6A, the vehicle recognition system recognizes the vehicle motion in the 2000th frame using the motion recognition system based on the above-described LK Optical flow. 6B shows an embodiment in which the motion of the recognized vehicle is continuously recognized and selected as the detection area.

According to the number recognition system using the macroblock-based motion recognition of the present invention, it is possible to prevent the problem of erroneous detection of continuously detecting an object other than the vehicle to be interrupted in the detected image, , It is possible to solve the erroneous portion due to the object (banner, etc.) similar to the car number in the surrounding environment.

In addition, since it is unnecessary to perform unnecessary arithmetic operations, it is possible to reduce the recognition result difference depending on the computer performance, thereby improving the interruption rate to the illegally parked vehicle.

The present invention can also be embodied as computer-readable codes on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like, and may be implemented in the form of a carrier wave (for example, transmission via the Internet) . The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers of the technical field to which the present invention belongs.

It should be understood that the above-described apparatus and method are not limited to the configurations and methods of the embodiments described above, but the embodiments may be modified such that all or some of the embodiments are selectively combined .

Claims (14)

delete delete delete delete A camera for photographing a first image associated with a plurality of objects;
A memory for storing motion vector information for the vehicle among the plurality of objects; And
And a controller for estimating a first motion vector of each of the plurality of objects from motion of the plurality of objects,
Wherein,
Detecting a change in brightness between any two consecutive images constituting the first image derived by the movement of the plurality of objects, estimating the first motion vector using the detected brightness change,
The first motion vector is compared with the stored motion vector information to recognize the vehicle among the plurality of objects,
When the motion value, which is an absolute value of the first motion vector of the first macro block, which is at least a part of the divided macroblock, is 1/4 or more,
Wherein the first macroblock is divided into N * M sub-macroblocks, and a motion vector of a sub-macroblock having a largest motion value among the sub-macroblocks divided is used as a motion vector of the first macroblock Number recognition system. 6. The method of claim 5,
Wherein,
Wherein if the motion value of the first motion vector of the first macro block is less than 1/4 of the absolute value of the motion vector of the first macroblock, it is determined that there is no motion. The method according to claim 5 or 6,
Wherein,
And recognizes the recognized text of the number plate of the vehicle. delete delete delete delete A first step of photographing a first image related to a plurality of objects;
A second step of estimating a first motion vector of each of the plurality of objects from motion of the plurality of objects;
A third step of recognizing a vehicle among the plurality of objects by comparing the first motion vector with motion vector information;
A fourth step of dividing the image into macroblocks having the same size;
When the motion value, which is an absolute value of the first motion vector of the first macro block, which is at least a part of the divided macroblock, is 1/4 or more,
Dividing the first macroblock into N * M sub-macroblocks; And
And a sixth step of making a motion vector of a lower macroblock having the largest motion value among the divided lower macroblocks as a motion vector of the first macroblock,
The second step may include detecting a change in brightness between two consecutive images constituting the first image derived from the motion of the plurality of objects and estimating the first motion vector using the detected brightness change In addition,
Wherein the motion vector information includes motion vector information for a vehicle image. 13. The method of claim 12,
Further comprising, after the sixth step, determining that there is no motion when the motion value of the first motion vector of the first macro block is less than 1/4. The method according to claim 12 or 13,
And recognizing the text of the license plate of the recognized vehicle.

Images