KR101319508B1 - The system and the method for monitoring illegal stopping and parking vehicles using an enhanced focus degradation method - Google Patents

Abstract

PURPOSE: An enhanced focus degradation method capable of acquiring clearer images from the unmanned camera is provided to effectively regulate the illegal parking and stopping vehicle through accurate vehicle number recognition. CONSTITUTION: The monitoring system functions once the scanning camera takes a picture of a vehicle parking and stoppage in the no-parking and stopping zone (S100). Once, it is confirmed as the illegal parking, the system controls to take a picture of the secure image of the license plate of the vehicle (S200). The multiple characters of the license plate is recognized clearly (S300) by using the first secure image among the multiple images. With the first reconstructed image (S400), the multiple characters of the license plate is recognized clearly. By comparing the recognition results, the characters which were sensed as the most frequent ones are recognized as the each letter of the vehicle number (S500). [Reference numerals] (AA) Start; (BB) End; (S100) Scan a vehicle parking and stoppage in the no-parking and stopping zone; (S200) Take a picture of the secure image of the license plate of the vehicle; (S300) Recognize first character in defined area section of the secure image; (S400) Recognized second character by applying improved focus degradation method to the secure image; (S500) Recognize as the most frequent one among first character recognition and second character recognition

Description

ILLEGAL STOPPING AND PARKING VEHICLES USING AN ENHANCED FOCUS DEGRADATION METHOD}

The present invention relates to a system and a method of controlling an illegal parking vehicle in a prohibited area for parking, and more particularly, to obtain an accurate vehicle number by securing a clear image of an image taken by an intermittent camera using an improved focus degradation method. The present invention relates to an illegal parking control system and a method for cracking down on illegal parking vehicles, which can perform recognition.

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 . Stopping means that the driver stops the vehicle without exceeding 5 minutes and is a non-parking stop.

In general, vehicles tend to park on either side of the road (or on the shoulder). 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 it can cause the conflict with the civilian person or friction with the civilian person during the enforcement.

Therefore, a method of controlling an illegal parking vehicle by installing an unmanned surveillance camera in a parking prohibited area has been widely used. The method of controlling by the unmanned surveillance camera may be performed by installing a surveillance camera on a parking prohibited area to detect the presence of an illegal parking vehicle.

In the conventional illegal parking vehicle control system using a surveillance camera, the detection camera is used to detect the presence of illegal parking vehicles for each channel of the prohibited parking area, and the detection camera is controlled using an intermittent camera that can perform pan, tilt and zoom operations. Was done in a way to crack down on old vehicles.

However, if the illegal parking vehicle is photographed at a long distance by using an intermittent camera, the focus may not be correct due to image blur, deterioration of focus, calibration error, etc. when the license plate is recognized. There was a problem that could be.

In addition, as the camera shakes due to external factors such as wind or vibration, deterioration in image quality may occur frequently, which may cause misrecognition or unrecognition of license plate characters.

Therefore, there is a demand for the development of an illegal parking control system and a method for controlling an illegal parking that can perform an efficient control by improving the image quality of the image photographed by the control camera.

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

The present invention has been made to solve the above conventional problems, by using the improved focus deterioration method to secure accurate image number from the image taken by the intermittent camera can perform accurate vehicle number recognition, effectively The purpose of the present invention is to provide a user with an illegal parking control system and a method for controlling an illegal parking vehicle.

Specifically, the illegal parking vehicle enforcement system and the enforcement of the crackdown of illegal parking vehicles that exist at a long distance can be made easier, the cracking distance can be increased, and the recognition rate of the license plate at night can be improved. The purpose is to provide the user with a method.

In addition, the objective of the present invention is to provide a user with an illegal parking control system and control method that can effectively perform image restoration using an improved focus degradation method even when performing a general security function.

In addition, the object of the present invention is to provide a user with an illegal parking control system and control method that can efficiently detect a vehicle and compensate for blind spots.

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.

The illegal parking control system according to an example of the present invention for realizing the above-described problem includes an intermittent camera for photographing an interrupted image by performing at least one of a pan, tilt, and zoom operation, and a parking prohibition. If it is determined that the vehicle has parked in the prohibited parking area using the detection camera and the detection image for photographing the detection image of the area, the control camera controls to photograph the control image of the license plate of the vehicle, And a controller for recognizing a character of the license plate by using the captured image, wherein the controller includes an improved focus on the first intermittent image and the first intermittent image, which are at least some of a plurality of images constituting the intermittent image. The vehicle number is detected by detecting a character for the first reconstructed image obtained by applying an enhanced focus degradation method. It can recognize the letters of the plate.

On the other hand, the illegal parking stop control system according to another example of the present invention for realizing the above-described problem, a high-resolution camera for shooting the image, the detection camera for taking a detection image for the parked prohibited area and the vehicle using the detection image If it is determined that the parking stop in the parked prohibited area, the high-resolution camera is controlled to shoot the control image of the license plate of the vehicle, and the control unit for recognizing the character of the license plate using the captured image The control unit may include a first reconstructed image obtained by applying an improved focus degradation method to the first intermittent image and the first intermittent image, which are at least some of the plurality of images constituting the intermittent image. The character of the license plate may be recognized by detecting a character.

In addition, the improved focus deterioration method may be a combination of a high resolution image generation method and a detailing method.

In addition, to perform the high resolution image generation method, the control unit, the image estimating means for up-scaling (up-scaling) the first intermittent image having a deterioration of focus according to a preset up-scale coefficient And image generating means for generating a high resolution image from which at least a portion of the focal deterioration is removed by applying bicubic interpolation to the first intermittent image and the up-scaled image.

The controller may further include image restoring means for removing at least a portion of the focal deterioration from the generated high resolution image by using a guided filter.

In addition, the first intermittent image may be plural, and the improved focus degradation method may extract at least one image capable of character recognition by repeatedly overlapping consecutive images among the plurality of first intermittent images.

In addition, the vehicle license plate includes a plurality of characters, and the control unit repeatedly performs the operation of recognizing each of the plurality of characters to obtain a plurality of recognition results, and compares the plurality of recognition results with each other most frequently. The detected character may be controlled to be recognized as each of the plurality of characters.

The apparatus may further include a warning unit configured to output a warning guide broadcast or a warning guide for the vehicle stopped in the parking stop area.

The apparatus may further include a memory configured to store learning data including a feature vector of the vehicle image, wherein the controller extracts a first feature vector from the detection image using a vehicle recognition algorithm, and compares the first feature vector with the first feature vector. The learning data is compared to recognize a vehicle among the objects photographed in the detection image, and the memory is controlled to additionally store a feature vector of the recognized vehicle in the learning data, and the vehicle recognition algorithm is a SIFT (Scale). At least one of Invariant Feature Transform (SURF), Speeded Up Robust Features (SURF), Histogram of Oriented Gradients (HOG), Haar-like features, and Gabor filter may be used.

In addition, further comprising a support fixed to the ground, the first rung is coupled to the upper end of the support and the second rung is coupled to the upper end of the support and is formed at a first angle with the first rung, The detection camera is installed at the end of the first rung, the first camera is installed at the end of the second rung, and according to the position of the first camera, a first zone, which is a shooting blind spot, is located below the first camera. And the length of the second crossbar and the first angle are determined so that the detection camera is positioned at a position capable of photographing the first zone, and the vehicle is stopped in the first zone using the detection image. If it is determined that the control unit controls the omnidirectional camera to shoot the license plate of the vehicle, the first camera is the intermittent camera or the high resolution It may be a camera.

In the method of controlling an illegal parking control system according to an example of the present invention for realizing the above-described problem, the first step of detecting a vehicle parked in a parking prohibited area, the control camera includes pan, tilt, and zoom A second step of photographing an interrupted image of the license plate of the vehicle by performing at least one of zoom operations, and applying an improved focus degradation method to a first interrupted image that is at least a part of a plurality of images constituting the interrupted image; And a fourth step of extracting a first reconstructed image and a fourth step of recognizing a character of the vehicle license plate using the first intermittent image and the first reconstructed image, wherein the improved focus degradation method includes: It may be a combination of a generation method and a detailing method.

The vehicle license plate may include a plurality of characters, and the fourth step may include: a first character recognition step of recognizing each of the plurality of characters of the vehicle license plate using the first intermittent image; A second character recognition step of recognizing each of the plurality of characters of the license plate using the vehicle, repeatedly performing the first character recognition step and the second character recognition step to obtain a plurality of recognition results and the plurality of recognition results Comparing each other with each other may include recognizing the most frequently detected characters as each of the plurality of characters.

In addition, between the first character recognition step and the second character recognition step, an image estimation step of up-scaling the input image according to a preset up-scale coefficient and the input image And generating a high-resolution image in which at least a portion of the deterioration of focus is removed by applying bicubic interpolation to the up-scaled image, wherein the input image comprises: a first image having the deterioration of focus; It may be an interrupted video.

The method may further include repeating the image estimation step and the image generation step a predetermined number of times, wherein the input image of the repeated image estimation step may be an image generated in the image generation step.

The method may further include an image restoring step of removing at least a part of the focal deterioration from the generated high resolution image by using a guided filter.

In addition, the first intermittent image may be plural, and the improved focus degradation method may extract at least one image capable of character recognition by repeatedly overlapping consecutive images among the plurality of first intermittent images.

According to the present invention, an illegal parking stop control system and control that can perform accurate vehicle number recognition and effectively crack down an illegal parking vehicle by securing a clear image quality from an image taken by a speed camera using an improved focus degradation method The method can be provided to the user.

Specifically, the illegal parking vehicle enforcement system and the enforcement of the crackdown of illegal parking vehicles that exist at a long distance can be made easier, the cracking distance can be increased, and the recognition rate of the license plate at night can be improved. The method can be provided to the user.

In addition, even when performing a general security function, it is possible to provide a user with an illegal parking control system and control method that can effectively perform image restoration using an improved focus degradation method.

In addition, it is possible to efficiently provide a vehicle detection, and provide a user with an illegal parking control system and a method of cracking down to compensate for blind spots.

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.
Figure 1 shows an example of a block diagram of an illegal parking regulation 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 an illegal parking control system is installed according to an example of the present invention.
4 is a plan view of a structure in which an illegal parking control system is installed according to another example of the present invention.
5 is a flowchart illustrating a method for cracking down a vehicle in a parking prohibited area by the illegal parking control system according to an example of the present invention.
6 is a flowchart illustrating an improved focus degradation method that may be applied to an illegal parking control system related to an example of the present invention.
7A and 7B illustrate an example of improving image quality of an intermittent image by a high resolution image generation method applicable to the present invention.
8A to 8C show an image having deterioration before the dethering method is applied.
9A to 9C illustrate an example of image quality improvement by the dethering method applicable to the present invention.

Hereinafter, a preferred embodiment of the present invention will be described with reference to the drawings. In addition, the embodiment described below does not unduly limit the contents of the present invention described in the claims, and the entire configuration described in this embodiment is not necessarily essential as the solution means of the present invention.

Conventionally, in order to prevent traffic jams and congestion caused by illegal parking vehicles, surveillance cameras are installed in prohibited parking areas to control illegal parking vehicles.

However, when a license plate camera is photographed by a speed camera to stop a vehicle parked at a distance from an intermittent camera, shaking or error may occur, and the license plate recognition is performed using an image of inconsistent image quality. This could cause a problem of misrecognizing or not recognizing license plate information, which is one of the factors that lowers the regulation rate.

An object of the present invention is to propose an illegal parking control system and a method for controlling an illegal parking stop system, which can improve the efficiency of cracking down an illegal parking vehicle by improving the image quality of an image captured by a speed camera using an improved focus degradation method.

Hereinafter, the illegal parking control system proposed by the present invention will be described in detail.

Figure 1 shows an example of a block diagram of an illegal parking regulation system that can be applied to the present invention.

The illegal parking control 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. can do.

However, since the components shown in FIG. 1 are not essential, an illegal parking control system having more or fewer components may be implemented.

Hereinafter, the components will be described in order.

The camera module 100 processes an image frame such as a still image or a moving image obtained by photographing a parking stop area. The image processed by the camera module 100 may be stored in the memory 400 or transmitted to the outside through the communication unit 300. The processed image image may be displayed on the display 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 the detection camera 110, the intermittent camera 120, the high resolution camera 130, and the like. However, the present invention is not limited to such a configuration, and may include a configuration including other shooting means.

The detection camera 110 photographs the parking prohibited area, and may detect whether the vehicle enters the prohibited parking area using the photographed detection 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, even if the detection camera 110 is installed, it may not be necessary to enlarge and view a specific point of the prohibited parking area, and thus an intermittent camera 120 capable of performing pan, tilt, and zoom operations may be required.

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 in which a zoom-in image or a zoom-out image can be taken for a vehicle by rotating the camera at a designated x and y coordinate.

The high resolution camera 130 may photograph a vehicle parked in a parking prohibited area.

The intermittent camera 120 is an expensive device that photographs a license plate of a vehicle that is illegally parked in a parking prohibited area by performing a pan, tilt, and zoom operation. On the other hand, the high resolution camera 130 is relatively inexpensive and has a simple structure that can recognize the license plate of the illegally parked vehicle without the pan, tilt function.

The high resolution camera 130 may be installed in the present invention for the purpose of supplementing the expensive intermittent camera 120, and may recognize a character in the license plate of the vehicle by using the photographed image of the parking stop area.

The high resolution camera 130 may preferably have a performance of 2 million pixels or more.

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 210 may display (output) information processed by the illegal parking control system 10. For example, a UI (User Interface) or GUI (Graphic User Interface) associated with the illegal parking control 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.

In addition, the display unit 210 may be used as a light for controlling a crime prevention area when controlling an illegally parked vehicle at night or in a dark space or when using the illegal parking control system 10 for crime prevention.

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 occurrence of an event of the illegal parking control system 10. Examples of events occurring in the illegal parking control system 10 include illegal parking of vehicles in a prohibited parking area, crime in a crime prevention area, and the like.

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. [

On the other hand, the communication unit 300 is one or more modules that enable communication between the illegal parking regulation system 10 and the wired / wireless communication system or between the illegal parking regulation system 10 and the network in which the illegal parking regulation system 10 is located. It may include. 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 location information module 330 is a module for obtaining a location of the illegal parking system 10, and a representative example thereof is a GPS (Global Position System) 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 temporarily stores input / output data (for example, still images, moving images, and feature vector information thereof). It can also perform a function for. The memory 400 may also store a frequency of use of each of the data (eg, a frequency of use of each feature vector information).

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 illegal parking control system 10 may operate in connection with a web storage that performs a storage function of the memory 400 on the Internet.

On the other hand, the interface unit 500 serves as a passage with all external devices connected to the illegal parking control system 10. The interface unit 500 receives data from an external device, receives power, and transfers the power to each component inside the illegal parking control system 10, or transmits data inside the illegal parking control system 10 to an external device. do.

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.

Meanwhile, the controller 700 typically controls the overall operation of the illegal parking control 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, the controller 700 may control the camera module 100 to photograph a parking prohibited area or an illegal parking vehicle, and recognize license plate information of the illegal parking vehicle using the captured image.

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. [

On the other hand, Figure 2 shows an example of a block diagram of a control unit that can be applied to the present invention.

As shown in Figure 2, the control unit 700 that can be applied to an example of the present invention includes a vehicle recognition means 710, illegal parking determination means 720, license plate recognition means 730, image estimation means 740, Image generating means 750, image restoring means 760, camera control means 770, memory control means 780 may be included. 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 vehicle recognizing means 710 receives a detection image of a parked forbidden area photographed by the detection camera 110, and may extract a feature vector from the detection image by using a vehicle recognition algorithm.

The vehicle recognition algorithm is an algorithm for recognizing a vehicle that is an object of the illegal parking control system 10, and includes scale-invariant feature transform (SIFT), speeded up robust features (SURF), histogram of oriented gradients (HOG), and haar- You can use either the like features or the Gabor filter.

Here, the SIFT algorithm is a representative algorithm for extracting feature vectors of an image and has invariant characteristics in image rotation, scaling, shifting, partial illumination variation, and projective transform. The SIFT algorithm may extract properties such as the position, scale, and direction of the feature in consideration of the characteristic of the local image.

That is, in the first step, the sample point (or candidate pixel) is selected by searching for the maximum and minimum in the scale space generated by the difference-of-Gaussian (DOG) function (Scale-space extrema detection).

In the second step, keypoint localization is selected based on the stability value.

In the third step, one or more directions are assigned to each keypoint.

The last step is to create a keypoint descriptor using local image gradients.

A detailed description of the SIFT algorithm is given in detail in the article "Distinctive image features from scale-invariant keypoints".

In addition, the SURF algorithm finds features that are invariant to changes in the environment, taking into account changes in the environment such as size, lighting, and viewpoints from multiple images. The algorithm is greatly improved.

A detailed description of the SURF algorithm is given in detail in the article "Robust Interest Point Detection and Descriptor".

In addition, the HOG algorithm is based on the fact that the appearance and shape of a specific object in the image can be determined by the slope size or the distribution of the edge direction.

The HOG algorithm divides an image into a plurality of regions called cells, and generates a histogram of a slope or a corner of each cell to recognize a specific object.

A detailed description of the HOG algorithm is given in detail in the "Histograms of oriented gradients for human detection" article.

In addition, the Haar-like features algorithm can recognize a specific object using a prototype representing the feature information of the edge and a prototype representing the feature information of the line. This is described in detail in the paper "An Extended Set of Haar-like Features for Rapid Object Detection".

A detailed description of the Gabor filter algorithm is also provided in detail in "Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters."

The feature vector extracted by the vehicle recognition algorithm may be compared with the learning data stored in the memory 400.

Since the learning data includes a feature vector for a general vehicle image, the vehicle recognition unit 710 may determine whether there is a vehicle among the objects photographed in the detection image, and recognize the vehicle.

In the process of recognizing the vehicle from the detected image, a linear nearest point search may be used, which is determined according to the number of feature vectors having high similarity among the feature vectors to be compared.

However, such a linear nearest point search should be compared with all the learning data stored in the memory 400, so the amount of computation is too large and the calculation speed may be slow.

Therefore, a method of speeding up the search by creating an index related to the feature vector information in the training data may be used.

In addition, the vehicle recognizing means 710 may determine whether the vehicle enters the parking prohibited area and the position where the vehicle stopped in the parking prohibited area.

For this purpose, a motion detection algorithm that detects the motion of the vehicle or an image detection algorithm that contrasts the background image of the no-parking area with the image when the vehicle is parked can be used. Preferably, both algorithms can be used for more accurate vehicle detection. have.

On the other hand, the illegal parking determination means 720 may determine whether or not the vehicle parked on the parking prohibited area.

That is, when the vehicle recognizing means 710 receives the detection image photographed by the detection camera 110 and recognizes the vehicle in the stopped parking area, the illegal parking determination means 720 determines whether the vehicle is illegally parked. It is possible to determine whether to perform the intermittent processing.

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 determination unit 720 may determine whether the illegal parking of the vehicle is illegal by using the detection image photographed at a predetermined time interval.

That is, the illegal parking determining means 720 initially detects the presence of the vehicle in the prohibited parking zone, and controls the detection camera 110 to photograph the stopped parking zone again after a preset time elapses. To this end, the camera control means 770 may control the operation of the detection camera 110 together.

The vehicle recognizing means 710 receives a detection image photographed after the predetermined time elapses, and extracts a feature vector from the detection image by using a vehicle recognition algorithm.

The extracted feature vector is compared with the learning data stored in the memory 400, and the vehicle recognizing means 710 may determine whether there is a vehicle among the objects photographed in the detected image photographed after a predetermined time elapses. To be aware of.

If the illegal parking determination means 720 determines that the vehicle recognized in the detection image after the preset time elapses is the same as the vehicle recognized in the initial detection image, the vehicle is considered to have 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.

Meanwhile, the license plate recognition unit 730 may recognize an image of the license plate of the illegal parking vehicle by receiving an image captured by the intermittent camera 120 or the high resolution camera 130.

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

The first is to detect the feature region of the license plate using vertical and horizontal edge information from the captured image.

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

The third is to search the numbers and letters directly to detect the correct license plate.

When the location of the license plate is detected, the character recognition (Korean consonant + number) by template matching, the character recognition (Hangul vowel) based on structural features, and the internal recognition algorithm uses numbers, letters (consonants, vowels) to reduce misunderstanding. By classifying features in detail and reconfirming the recognized character, errors in character decryption can be minimized.

On the other hand, the image estimating means 740 is used when a high resolution image generation method is used as an improved focus degradation method.

The image estimating means 740 may generate a super-resolution image by up-scaling the low resolution degraded image according to an up-scale coefficient.

The image estimating means 740 receives the interrupted image from the intermittent camera 120 or the high resolution camera 130. When focus degradation occurs due to shaking or error in the received interrupted image, the image estimating unit 740 may predict the focused image from the image of the interrupted image.

In the case of an image having a deterioration of focus, an edge portion of a subject is blurred, and various algorithms may be used to predict actual edge information. Such algorithms are well known to those skilled in the art to which the present invention pertains, and detailed descriptions thereof will be omitted.

The image estimating means 740 obtains the super resolution image SR from the low resolution image in the intermittent image having the deterioration of focus by using the above algorithm, and estimates the focused image by using the algorithm.

On the other hand, the image generating means 750 is used when using a high resolution image generating method as an improved focus degradation method.

When the super resolution image is generated from the low resolution image inputted by the image estimating means 740 according to the up-scale coefficient, the image generating means 750 focuses using the super resolution image and the intermittent image. A high resolution image from which at least a portion of the degradation is removed may be generated, and the high resolution image is calculated by interpolation. In this case, the interpolation method may preferably improve the deterioration of the focus image by using bicubic interpolation.

The relationship between the deteriorated image and the high resolution image may be represented by Equation 1 below.

는 생성된 고해상도 영상이고,

은 저해상도 영상으로 입력된 초점열화이며,

는 저해상도 영상에서 업-스케일 계수에 따라 보간법을 적용한 초해상도 영상이다.here,

Is the generated high resolution image,

Is a deterioration of focus input as a low resolution image.

Is a super resolution image using interpolation according to the up-scale coefficient in the low resolution image.

The image generating means 750 may generate a high resolution image focused in accordance with Equation 1 in the intermittent image having the focus deterioration, and details of the generation will be omitted since it is obvious to a person skilled in the art.

On the other hand, the image restoring means 760 is used when using the detailing method as an improved focus deterioration method.

The image restoring means 760 receives a high resolution image that is in focus from an image having deterioration of focus, and uses a deterring method to improve sharpness.

When the image generating means 750 generates the high resolution image by receiving the intermittent image captured by the intermittent camera 120 or the high resolution camera 130, the image restoring means 760 focuses from the intermittent image using the generated high resolution image. Part of the degradation can be eliminated.

The removal of such focal deterioration may be made in plural.

That is, the image generating means 750 calculates a high resolution image by using the super resolution image estimated by the image estimating means 740, and the image restoring means 760 is used to improve the sharpness by the deterring method.

The image of which the image restoring unit 760 partially removes the focus deterioration is inputted to the image estimating unit 740 again to estimate the super resolution image, and the high resolution image is calculated again by the image generating unit 750. The image restoring means 760 uses this to remove the deterioration of focus.

This repeated process may be repeated according to the set parameter value.

In addition, a guided filter may be used as an example of the deterring method that may be used in the image restoring means 760. The guided filter is a local linear filter and has a property of smoothing while preserving edge components like the bilateral filter. This feature prevents the edges of the image from crushing and maintains the base layer.

According to the image generating means 750, the image quality is improved, but there may be local smoothing phenomenon and defects in the edge region, that is, artifacts about the object surroundings or feature information. To further improve this and obtain precise results, the guided filter can be used to obtain a clear, high quality image.

The guided filter performs the operation as shown in Equation 2 as a deterring method that can be applied to the present invention.

,

는 필셀위치를 나타내고,

는 필터 커널을 나타내며,

는 입력영상을 나타내고,

는 선형변환(guidance) 영상을 나타낸다.In Equation (2)

,

Represents the pixel position,

Represents the filter kernel,

Indicates the input image,

Denotes a linear transformation image.

The filter kernel of Equation 2 may be expressed as Equation 3 below.

는 선형변환 영상이고,

는 필터 커널을 나타내며,

는 분산이고,

은 정규화된 파라미터이고, 는

의

변환영상에서의 평균이며,

는

의 커널 중심의 픽셀 위치이다.In Equation (3)

Is the linear transformation image,

Represents the filter kernel,

Is variance,

Is a normalized parameter, The

of

Is the mean in the transformed image,

The

Kernel center pixel location.

On the other hand, the camera control means 770 may control the overall operation of the detection camera 110, the intermittent camera 120, the high-resolution camera 130, etc. belonging to the camera module 100.

The camera control unit 770 may control the illegal parking stop control system 10 to capture a detection image for the prohibited parking area using the detection camera 110 to control a vehicle stopped in the prohibited parking area.

In addition, the camera control unit 770 may control to photograph the detection image for the parked prohibited area again after a preset time so as to determine whether the vehicle stopped in the parked prohibited area is parked on the parked prohibited area. have. This may be controlled together with the illegal parking determination means 720.

In addition, the camera control means 770 receives the position information of the stationary vehicle determined by the vehicle recognition means 710, and by using this, the intermittent camera 120 can photograph the license plate of the vehicle stopped in the stop area. The control may be performed to perform at least one of the pan, tilt, and zoom operations of the intermittent camera 120.

In addition, the camera control means 770 may control the operation of the high-resolution camera 130 so that the high-resolution camera 130 can take a picture of the vehicle parked in the parking stop zone.

On the other hand, the memory control means 780 may control the overall operation of the various data input / output to the memory 400.

The vehicle recognizing means 710 of the control unit 700 extracts a feature vector from the detected image, and compares the extracted feature vector with feature vector information of a general vehicle image of the memory 400.

To this end, the memory control means 780 may control the memory 400 to output the learning data including the feature vector information of the general vehicle image to the vehicle recognition means 710.

In addition, when the feature vector information on the vehicle recognized by the vehicle recognition means 710 is not present in the training data of the memory 400, the feature vector information may be stored in the memory (for comparison with the next training data). 400).

To this end, the memory control means 780 may control to input the feature vector information on the vehicle recognized by the vehicle recognition means 710 into the memory 400.

Hereinafter, the installation structure of the illegal parking control system having the above-described configuration will be described with reference to FIGS. 3A, 3B, and 4.

3A and 3B are a plan view and a side view of a structure in which an illegal parking control system is installed according to an example of the present invention.

As shown in FIGS. 3A and 3B, the illegal parking control system 10 structure of the present invention may include a support 12, a crossbar 14, a detection camera 110, and a control camera 120.

However, since the components shown in FIGS. 3A and 3B are not essential, an illegal parking control system having more or fewer components may be configured. Hereinafter, the installation structure of FIGS. 3A and 3B 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 strut 12 is internal so that the wire connected from the ground can be penetrated to supply power to the detection camera 110, the intermittent camera 120, the high resolution camera 130, the output unit 200, the communication unit 300, and the like. It may be formed in a hollow, the material is preferably formed of a metal material that does not corrode rain water.

One crossbar 14 may be connected to and installed on an upper portion of the support 12. Like the support 12, the inside of the support 12 may be hollow, and the material is preferably formed of a metal material.

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

The detection camera 110, the intermittent camera 120, and the high resolution camera 130 may process an image frame such as a still image or a moving image obtained by photographing a parking stop area. The detection camera 110, the intermittent camera 120, and the high resolution camera 130 may be installed at an end portion of the crossbar 14, and preferably, may be disposed above the parking stop area to be controlled.

On the other hand, Figure 4 is a plan view of a structure in which an illegal parking control system according to another example of the present invention is installed.

As in the structure of Figs. 3a and 3b, the post is fixed to the ground in or near the parking prohibition area, and is preferably fixed to the ground or inserted into the ground by bolts.

The inside of the support may be formed in a hollow, the material is preferably formed of a metal material that does not corrode rain.

A crossbar 14 may be installed and connected to an upper portion of the support, and the inside of the support may be hollow, and the material may be formed of a metal material.

The crossbar 14 may include a first crossbar 14a and a second crossbar 14b. However, the present invention is not limited to such a configuration, and may include a configuration having more crossbars.

The first crossbar 14a and the second crossbar 14b are formed at a predetermined angle, and the angle may be determined according to the site conditions of the prohibited parking area so as to smoothly control the illegal parking vehicle.

In addition, the first crossbar 14a and the second crossbar 14b may be positioned horizontally with respect to the ground, and may preferably be disposed above the parking stop area.

The first crossbar 14a or the second crossbar 14b may be installed in a structure that is coupled with the support such that the first crossbar 14a or the second crossbar 14b may be rotated about the support 100. In this case, the angle formed between the first crossbar 14a and the second crossbar 14b is changed by rotating the first crossbar 14a or the second crossbar 14b, and thus, the intermittent camera 120 or the high resolution camera ( The position of the detection camera 110 may be adjusted to complement the blind spot of 130.

The detection camera 110 may be installed at the end of the first crossbar 14a, preferably disposed above the parking prohibited area, and may detect a vehicle entering the parking prohibited area.

The intermittent camera 120 may be installed at the end of the second crossbar 14b, and may be preferably disposed on the parking prohibited area, and illegally parks in the parking prohibited area by performing pan, tilt, and zoom operations. You can photograph the license plate of a vehicle.

The controller 700 may determine whether the location of the vehicle parked in the prohibited parking area is within the blind spot of the control camera 120.

If it is determined that the position of the vehicle is within the blind spot of the intermittent camera 120, the intermittent camera 120 does not operate because the illegal parking vehicle cannot be photographed. In order to compensate for the blind spot of the control camera 120, the camera control means 770 may control the detection camera 110 to photograph the illegal parking vehicle.

If it is determined that the position of the vehicle is not within the blind spot of the intermittent camera 120, the camera control means 770 controls the intermittent camera 120 to perform at least one of pan, tilt and zoom operations so that the license plate of the illegally parked vehicle is stopped. You can shoot.

A high resolution camera 130 may be installed at the end of the second crossbar 14b instead of the intermittent camera 120.

The high resolution camera 130 may also photograph a vehicle parked in a parking prohibited area. If the intermittent camera 120 performs a pan, tilt, or zoom operation and is an expensive device for photographing a license plate of a vehicle that is illegally parked in a parking prohibited area, the high resolution camera 130 is illegally parked even without a pan and tilt function. It is relatively inexpensive and has a simple structure that can recognize the license plate of a vehicle.

Meanwhile, a high resolution camera 130 may be additionally installed at the end of the first crossbar 14a. Here, the high resolution camera 130 may supplement the shooting blind spot of the intermittent camera 120 and photograph the license plate of the illegally parked vehicle, and may preferably have a performance of 2 million pixels or more.

Hereinafter, a method of controlling an illegal parking control system having the above-described structure will be described with reference to FIG. 5.

5 is a flowchart illustrating a method for cracking down a vehicle in a parking prohibited area by the illegal parking control system according to an example of the present invention.

Referring to FIG. 5, first, the detection camera 110 detects an illegal parking vehicle by photographing a detection image for a prohibited parking area (S100).

In operation S100, the omnidirectional camera including the fisheye lens may be used as the detection camera 110.

In this case, the control unit 700 may restore the standard image with the aspect ratio adjusted by correcting the distortion of the omnidirectional image photographed by the omnidirectional camera, and detect the illegal parking vehicle in the parking prohibited area using the standard image. have.

In addition, the vehicle recognition means 710 receives the detection image photographed by the detection camera 110, the vehicle can be recognized using a vehicle recognition algorithm.

The vehicle recognizing means 710 may extract feature vector information by applying a vehicle recognition algorithm to the detection image, and compare the information with the learning data stored in the memory 400 to recognize the vehicle among the objects photographed in the detection image. .

As the vehicle recognition algorithm, a scale-invariant feature transform (SIFT), speeded up robust features (SURF), histogram of oriented gradients (HOG), haar-like features, and a gabor filter may be applied.

By using the vehicle recognition algorithm, it is possible to solve the problem that an object other than the vehicle existing around the forbidden parking area is misdetected.

In addition, the illegal parking determination means 720 may determine whether the vehicle is illegally parked. To this end, after a predetermined time or more elapses, the parking stop zone is photographed again by the detection camera 110, and the vehicle recognition process is performed again using the photographed detection image.

Subsequently, when it is determined that the vehicle is illegally parked by the illegal parking determination unit 720, the camera control unit 770 operates the pan, tilt, and zoom operations of the intermittent camera 120. At least one of the control is performed to shoot a control image of the license plate of the vehicle (S200).

In step S200, instead of the intermittent camera 120, a high-resolution camera 130 may be used to capture a control image of the vehicle.

When the high resolution camera 130 is used, an illegal parking control system can be installed at a lower cost than the expensive control camera 120 having a pan, tilt, and zoom function, and there is an advantage in that maintenance and management are easier.

Subsequently, the license plate recognizing means 730 recognizes each of a plurality of characters of the license plate by using a first intermittent image that is at least a part of a plurality of images constituting the intermittent image (S300).

Character recognition method of the license plate recognition means 730 is the same as described above.

Subsequently, the first reconstructed image is extracted by applying an improved focus degradation method to the first intermittent image, and the license plate recognizing means 730 recognizes each of the plurality of characters of the vehicle license plate using the first reconstructed image ( S400).

As an improved focus degradation method, at least one of a high resolution image generation method and a detailing method may be used, and an algorithm applicable to the present invention is not limited thereto. Preferably, a plurality of first reconstructed images may be generated by simultaneously using a high resolution image generating method and a deterring method.

In addition, by using the improved focus degradation method, a first reconstructed image capable of character recognition by the license plate recognizing means 730 may be extracted by repeatedly overlapping a continuous image among a plurality of first intermittent images.

7A and 7B will be described first to describe an improvement in image quality of an interrupted image by a high resolution image generation method. 7A and 7B illustrate an example of improving image quality of an intermittent image by a high resolution image generation method applicable to the present invention. FIG. 7A illustrates an image before a high resolution image generation method is applied to an interrupted image, and FIG. 7B illustrates an interrupted image to which a high resolution image generation method is applied.

As shown in FIG. 7A, an illegal parking vehicle located at a distant distance may not be vividly photographed due to shaking or an error. Therefore, it is difficult to recognize the license plate letters of illegal parking vehicles, there was a problem that may be incorrectly recognized.

However, when the high resolution image generation method is applied to the intermittent image, the desired information may be extracted by superimposing successive images constituting the intermittent image, and as shown in FIG. 7B, a clear image may be obtained, thereby illegal parking vehicle. License plate character recognition can be enabled.

6 to describe the reconstructed image improved from the deterioration of focus. 6 is a flowchart illustrating an improved focus degradation method that may be applied to an illegal parking control system related to an example of the present invention.

Referring to FIG. 6, first, a super-resolution image may be generated by up-scaling according to an up-scale coefficient in a first intermittent image having deterioration of focus. (S410).

Subsequently, a high resolution image is calculated by applying bicubic interpolation to the first intermittent image and the generated super resolution image (S420), and a part of the focus deterioration from the first intermittent image using the calculated high resolution image. Remove (S430).

Steps S410 to S430 may be repeated according to values of preset coefficients, and preferably may be repeated until focus deterioration is no longer improved (S440).

After performing steps S410 to S420 repeatedly, a high resolution image from which a part of the focus deterioration is removed may be obtained. In step S430, a deterring method is used to restore the generated high resolution image to a clear image having a visually good quality. Use

When the deterioration of focus can be improved, the super resolution image may be estimated using the image generated in operation S430, and a part of the focus deterioration may be removed by calculating a high resolution image.

If the deterioration of the focus is not possible, the license plate recognizing means 730 may recognize the character of the license plate using the first reconstructed image generated in operation S430 (S450).

In addition, the improved focus deterioration method may use a multi-scale processing method that obtains a result from a downsampled image and then applies the result to a large image to effectively estimate a large motion deterioration. have.

In other words, after the deterioration is obtained from the small size image, it may be used as the next large input image by using bilinear interpolation.

Also, steps S410 to S420 may be repeatedly performed according to preset coefficients to obtain a clear high resolution image, and the dethering method of step S430 is performed on the high resolution image obtained by the repetition to restore a clear image. It is also possible.

8A to 8C and 9A to 9C will be described to explain the improvement of the quality of the interrupted image by the deterring method. 8A to 8C illustrate an image before the dethering method is applied to the intermittent image, and FIGS. 9A to 9C illustrate an intermittent image to which the deterring method is applied.

As illustrated in FIGS. 9A to 9C, when the dethering method is applied to the images of FIGS. 8A to 8C in which deterioration of focus is caused by shaking or an external factor, an image having a clear image quality may be extracted. Therefore, the license plate character recognition by the license plate recognition means 730 can be made easier.

Referring back to FIG. 5, the license plate recognizing means 730 compares the plurality of recognition results of steps S300 and S400 with each other and recognizes the most frequently detected character as each license plate character of the vehicle (S500). .

The license plate of the vehicle is composed of a plurality of characters, and the license plate recognition unit 730 may recognize each of the plurality of characters of the vehicle license plate using the first intermittent image.

In addition, the license plate recognition unit 730 may recognize each of a plurality of characters of the license plate using the first reconstructed image. The first reconstructed image may be an image extracted by applying an improved focus degradation method to the first intermittent image several times, and the first reconstructed image may be plural.

The plurality of recognition results may be different letters. In this case, the letters most frequently detected may be recognized as letters on the license plate by comparing the plurality of recognition results with each other.

According to the illegal parking stop control system and control method using the improved focus deterioration method of the present invention described above, it is possible to improve the quality of the control image taken by the control camera to improve the intermittent distance, and difficult to shoot at night. In this case, illegal parking vehicle enforcement may be conducted. In addition, even when illegal parking control system is used to perform a general life security function, more effective crime prevention can be performed according to image quality improvement.

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 (16)

An intermittent camera that captures an intermittent image by performing at least one of a pan, tilt, and zoom operations;
A detection camera for photographing a detection image for a prohibited parking area; And
If it is determined that the vehicle has parked at the stop area forbidden using the detection image, the camera controls the camera to shoot the cracked image of the license plate of the vehicle, and the vehicle license plate is photographed using the photographed crackdown image. A control unit for recognizing a character of the, including;
The controller detects a character for a first reconstructed image obtained by applying an enhanced focus degradation method to a first intermittent image and the first intermittent image that is at least a part of a plurality of images constituting the intermittent image, Recognize the letters on the license plate,
The focal deterioration method is a combination of a high resolution image generation method and a detailing method,
In order to perform the high resolution image generation method, the control unit,
Image estimating means for up-scaling the first intermittent image with deterioration of focus according to a predetermined up-scale coefficient; And
Image generating means for generating a high resolution image from which at least a portion of the focal deterioration is removed by applying bicubic interpolation to the first intermittent image and the up-scaled image; Parking enforcement system. A high resolution camera for photographing interrupted video;
A detection camera for photographing a detection image for a prohibited parking area; And
If it is determined that the vehicle has parked in the prohibited area using the detection image, the high-resolution camera controls the camera to photograph the enforcement image of the license plate of the vehicle, and uses the photographed enforcement image to photograph the vehicle license plate. A control unit for recognizing a character of the, including;
The controller detects a character for a first reconstructed image obtained by applying an enhanced focus degradation method to a first intermittent image and the first intermittent image that is at least a part of a plurality of images constituting the intermittent image, Recognize the letters on the license plate,
The focal deterioration method is a combination of a high resolution image generation method and a detailing method,
In order to perform the high resolution image generation method, the control unit,
Image estimating means for up-scaling the first intermittent image with deterioration of focus according to a predetermined up-scale coefficient; And
Image generating means for generating a high resolution image from which at least a portion of the focal deterioration is removed by applying bicubic interpolation to the first intermittent image and the up-scaled image; Parking enforcement system. delete delete 3. The method according to claim 1 or 2,
The control unit to perform the deterring method,
And an image restoring means for removing at least a portion of the deterioration of focus from the generated high resolution image using a guided filter. 3. The method according to claim 1 or 2,
The first intermittent image is plural,
The focal deterioration method is illegal illegal parking control system, characterized in that for extracting at least one image capable of character recognition by repeatedly overlapping successive images of the plurality of first intermittent images. 3. The method according to claim 1 or 2,
The license plate includes a plurality of characters,
The control unit,
Repeating the operation of recognizing each of the plurality of characters to obtain a plurality of recognition results,
And comparing the plurality of recognition results with each other to control the most frequently detected character to be recognized as each of the plurality of characters. 3. The method according to claim 1 or 2,
And a warning unit configured to output a warning guide broadcast or a warning guide for the vehicle stopped in the prohibited parking area. 3. The method according to claim 1 or 2,
A memory for storing the training data including the feature vector for the vehicle image;
The controller extracts a first feature vector from the detection image by using a vehicle recognition algorithm, compares the first feature vector with the training data, and recognizes a vehicle among objects photographed in the detection image. Control to further store a feature vector of the recognized vehicle in the learning data;
The vehicle recognition algorithm may use at least one of a scale-invariant feature transform (SIFT), speeded up robust features (SURF), histogram of oriented gradients (HOG), haar-like features, and a gabor filter. system. The method of claim 1,
Props fixed to the ground;
A first crossbar having one end coupled to an upper portion of the support; And
One end is coupled to the upper portion of the support, and the second crosspiece is installed to form a first angle with the first crossbar; further comprising,
The detection camera is installed at the end of the first crosspiece,
The intermittent camera is installed at the end of the second crossbar,
According to the position of the intermittent camera, a first zone, which is a shooting blind spot, is generated below the intermittent camera,
The length and the first angle of the second rung are determined such that the detection camera is disposed at a position capable of photographing the first zone,
And if it is determined that the vehicle is stopped in the first zone by using the detection image, the controller controls the detection camera to photograph the license plate of the vehicle. The method of claim 2,
Props fixed to the ground;
A first crossbar having one end coupled to an upper portion of the support; And
One end is coupled to the upper portion of the support, and the second crosspiece is installed to form a first angle with the first crossbar; further comprising,
The detection camera is installed at the end of the first crosspiece,
The high resolution camera is installed at the end of the second crossbar,
According to the position of the high resolution camera, a first zone, which is a shooting blind spot, is generated below the high resolution camera,
The length and the first angle of the second rung are determined such that the detection camera is disposed at a position capable of photographing the first zone,
And if it is determined that the vehicle is stopped in the first zone by using the detection image, the controller controls the detection camera to photograph the license plate of the vehicle. A first step of detecting a vehicle parked in a no parking zone;
A second step in which the intermittent camera photographs the intermittent image of the license plate of the vehicle by performing at least one of pan, tilt, and zoom operations;
A third step of extracting a first reconstructed image by applying an enhanced focus degradation method to a first intermittent image that is at least a part of a plurality of images constituting the intermittent image; And
And a fourth step of recognizing a character of the license plate using the first intermittent image and the first reconstructed image.
The focal deterioration method is a combination of a high resolution image generation method and a detailing method,
The vehicle license plate includes a plurality of characters,
The fourth step,
A first character recognition step of recognizing each of a plurality of characters of the license plate by using the first intermittent image;
A second character recognition step of recognizing each of a plurality of characters of the vehicle license plate using the first reconstructed image;
Repeating the first character recognition step and the second character recognition step to obtain a plurality of recognition results; And
And comparing the plurality of recognition results with each other to recognize the most frequently detected characters as each of the plurality of characters. 13. The method of claim 12,
Between the first character recognition step and the second character recognition step,
An image estimation step of up-scaling the input image according to a preset up-scale coefficient; And
An image generation step of generating a high resolution image from which at least a portion of the focal deterioration is removed by applying bicubic interpolation to the input image and the up-scaled image;
And the input image is the first interrupted image having the deterioration of focus. The method of claim 13,
Repeating the image estimating step and the image generating step a predetermined number of times;
And the input image of the repeated image estimating step is an image generated in the image generating step. The method of claim 13,
And an image restoring step of removing at least a portion of the deterioration of focus from the generated high resolution image by using a guided filter. The method of claim 12 ,
The first intermittent image is plural,
The method of deteriorating focus may include extracting at least one image capable of character recognition by repeatedly overlapping successive images among the plurality of first interrupted images.

Images