KR102612655B1 - Illegal parking enforcement system capable of determining intentional license plate obscuration - Google Patents

Abstract

An illegal parking enforcement system that can determine whether vehicle license plates are intentionally obscured has been launched. CCTV device that generates CCTV images; A parking/stopped vehicle license plate recognition device that recognizes the license plate number of a parked/parked vehicle from the CCTV image generated by the CCTV device; A parking/stopped vehicle control device that controls the parked/stopped vehicle using the license plate number recognized by the parked/stopped vehicle license plate recognition device; When the license plate number recognition device for the parked/stopped vehicle does not recognize the license plate number, a license plate blocking vehicle determination device that determines whether the parked/stopped vehicle is a license plate blocking vehicle; When the vehicle is determined to be a license plate occluded vehicle by the license plate occluded vehicle identification device, an alarm device for the occurrence of a license plate occluded vehicle is configured to output an alarm regarding the occurrence of a license plate occluded vehicle. According to the illegal parking enforcement system capable of determining the intentional blocking of license plates described above, it is configured to identify vehicles with intentional blocking of license plates in the video and output this through an alarm or enforcement text, thereby preventing intentional license plate blocking and conducting on-site crackdowns. It is also effective in eradicating illegal parking.

Description

Illegal parking enforcement system capable of determining intentional vehicle license plate blocking {ILLEGAL PARKING ENFORCEMENT SYSTEM CAPABLE OF DETERMINING INTENTIONAL LICENSE PLATE OBSCURATION}

The present invention relates to an illegal parking enforcement system, and more specifically, to an illegal parking enforcement system capable of determining intentional vehicle license plate blocking.

The existing illegal parking enforcement system detects vehicles parked/stopped in no-parking areas on the road using CCTV cameras, zooms in using the PTZ (pan, tilt, zoom) function, and automatically recognizes the vehicle license plate. They are cracking down.

However, recently, intentional blocking of license plates of parked/stopped vehicles has occurred frequently.

Since illegal parking enforcement is impossible when the vehicle license plate is obscured, there is a problem in that the illegal parking enforcement system is effectively rendered ineffective.

Accordingly, a method is needed to identify and guide or crack down on illegally parked vehicles that intentionally cover their license plates.

Registered Patent Publication 10-1784449 Registered Patent Publication 10-0834013

The purpose of the present invention is to provide an illegal parking enforcement system capable of determining intentional blocking of a vehicle license plate.

The illegal parking enforcement system capable of determining intentional blocking of vehicle license plates according to the purpose of the present invention described above includes a CCTV device that generates CCTV images; A parking/stopped vehicle license plate recognition device that recognizes the license plate number of a parked/parked vehicle from the CCTV image generated by the CCTV device; A parking/stopped vehicle control device that controls the parked/stopped vehicle using the license plate number recognized by the parked/stopped vehicle license plate recognition device; If the license plate number recognition device for the parked/stopped vehicle does not recognize the license plate number, it may be configured to include a license plate blocking vehicle determination device that determines whether the parked/stopped vehicle is a license plate blocking vehicle.

Here, when the vehicle is determined to be a license plate occluded vehicle by the license plate occluded vehicle discrimination device, it may be configured to further include a license plate occluded vehicle occurrence alarm device that outputs an alarm regarding the occurrence of a license plate occluded vehicle.

And the CCTV device includes a CCTV camera module that generates CCTV images of the parked/stopped vehicle and the corresponding license plate; a CCTV image storage module that stores CCTV images generated by the CCTV camera module; When a parked/stopped vehicle is detected in the CCTV image, the CCTV camera module may be configured to include a license plate enlargement control module that controls the vehicle license plate to be enlarged and captured.

And the parked/stopped vehicle license plate recognition device includes a parked/stopped vehicle detection module that detects a parked/stopped vehicle in the CCTV image; It may be configured to include a parked/stopped vehicle license plate detection module that detects the license plate of the parked/stopped vehicle detected by the parked/stopped vehicle detection module.

And the license plate occlusion vehicle identification device detects the parked/stopped vehicle detected by the parked/stopped vehicle detection module when the license plate of the parked/stopped vehicle is not detected in the parked/stopped vehicle license plate detection module. A vehicle detection box overlap determination module that determines the overlap between boxes; If overlap between vehicle detection boxes occurs as a result of the determination of the vehicle detection box overlap determination module, the parked/stopped vehicle license plate detection module determines that the parked/stopped vehicle whose license plate is not detected is blocked by the vehicle. , If there is no overlap of vehicles but the vehicle license plate is not detected, it is determined as intentional blocking of the vehicle license plate. It may be configured to include a first license plate obscuring vehicle identification module.

And the parked/stopped vehicle license plate recognition device includes: a parked/stopped vehicle text detection module that detects characters from the license plate detected by the parked/stopped vehicle license plate detection module; A standard database for each license plate type in which specifications for the position and number of characters for each license plate type are stored in advance; a parked/stopped vehicle detection text confirmation module that checks the text detected by the parked/stopped vehicle text detection module by referring to specifications pre-stored in the specifications database for each license plate type; an empty character position cropping module that crops empty character positions when all characters are not identified according to the standard in the parked/stopped vehicle detection character confirmation module; If all characters are confirmed according to the standard in the parked/stopped vehicle detection text confirmation module, the vehicle number of the parked/stopped vehicle is recognized using the characters confirmed in the parked/stopped vehicle detection text confirmation module, or the parked/stopped vehicle If all characters are not confirmed according to the standard in the vehicle detection character confirmation module, the empty character position cropping module crops the empty character positions and recognizes individual characters for each cropped position to recognize the number of the parked/stopped vehicle. It may be configured to further include a parking/stopped vehicle license plate number recognition module.

And the license plate obscuring vehicle identification device is a second license plate obscuring device that determines the parked/stopped vehicle as a license plate obscuring vehicle when the number of the parked/stopped vehicle is not recognized in the parking/stopped vehicle license plate recognition module. It may be configured to further include a vehicle identification module.

According to the illegal parking enforcement system capable of determining the intentional blocking of license plates described above, it is configured to identify vehicles with intentional blocking of license plates in the video and output this through an alarm or enforcement text, thereby preventing intentional license plate blocking and conducting on-site crackdowns. It is also effective in eradicating illegal parking.

Figure 1 is an example of a scene where a vehicle license plate is covered.
Figure 2 is a block diagram of an illegal parking enforcement system capable of determining intentional blocking of a vehicle license plate according to an embodiment of the present invention.
Figure 3 is an example diagram of a license plate recognition image according to an embodiment of the present invention.
Figure 4 is an example of cropping the position of an empty character of a vehicle license plate according to an embodiment of the present invention.
Figure 5 is an example diagram of a vehicle detection box image according to an embodiment of the present invention.
Figure 6 is an exemplary diagram of a parking/stopped vehicle control device according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and detailed descriptions will be given for carrying out the invention. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. The term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

Figure 2 is a block diagram of an illegal parking enforcement system capable of determining intentional blocking of a vehicle license plate according to an embodiment of the present invention. And Figure 3 is an example of a license plate recognition image according to an embodiment of the present invention, Figure 4 is an example of cropping the location of empty characters of a license plate according to an embodiment of the present invention, and Figure 5 is an example of a license plate recognition image according to an embodiment of the present invention. This is an exemplary diagram of a vehicle detection box image according to an embodiment of the present invention, and Figure 6 is an exemplary diagram of a parking/stopped vehicle enforcement device according to an embodiment of the present invention.

First, referring to FIG. 2, the illegal parking enforcement system 100 capable of determining intentional license plate blocking according to an embodiment of the present invention includes a CCTV device 110, a parking/stopped vehicle license plate recognition device 120, and a main/stopped vehicle license plate recognition device 120. It may be configured to include a stopped vehicle control device 30, a vehicle license plate occluded vehicle identification device 140, and a license plate occluded vehicle alarm device 150.

Hereinafter, the detailed configuration will be described.

The CCTV device 110 may be configured to generate CCTV images for crackdown on illegally parked vehicles.

The CCTV device 110 may be configured to include a CCTV camera module 111, a CCTV image storage module 112, and a license plate enlargement control module 113.

Hereinafter, the detailed configuration will be described.

The CCTV camera module 111 may be configured to generate CCTV images of parked/stopped vehicles and their license plates.

The CCTV image storage module 112 may be configured to store CCTV images generated by the CCTV camera module 111.

When a parked/stopped vehicle is detected in a CCTV image, the license plate enlargement control module 113 can control the CCTV camera module 111 to enlarge and capture the corresponding license plate. First, you can use the PTZ (pan/tilt/zoom) function to capture the parked/stopped vehicle and control it to enlarge and capture the license plate.

The parking/stopped vehicle license plate recognition device 120 may be configured to recognize the license plate number of a parked/stopped vehicle from CCTV images generated by the CCTV device 110.

The parking/stopped vehicle license plate recognition device 120 includes a parked/stopped vehicle detection module 121, a parked/stopped vehicle license plate detection module 122, a parking/stopped vehicle character detection module 123, and specifications for each license plate type. It may be configured to include a database 124, a parked/stopped vehicle detection character confirmation module 125, an empty character location cropping module 126, and a parked/stopped vehicle license plate recognition module 127.

Hereinafter, the detailed configuration will be described.

The parked/stopped vehicle detection module 121 may be configured to detect parked/stopped vehicles in CCTV images.

Here, the parking/stopped vehicle detection module 121 uses DNN (Deep Neural Network) technology, and among these, CNN (Convolutional Neural Network), which has excellent performance in detecting objects in images, is used to detect parked/stopped vehicles. It can be configured. CNN can be configured to extract a number of feature components present in an image through a convolutional layer and determine the location and type of an object based on the extracted features.

The parked/stopped vehicle license plate detection module 122 may be configured to detect the license plate of the parked/stopped vehicle detected by the parked/stopped vehicle detection module 121.

Here, the parking/stopped vehicle license plate detection module 122 also uses DNN (Deep Neural Network) technology, and among these, CNN (Convolutional Neural Network), which demonstrates excellent performance in detecting objects in images, is used to detect vehicle license plates. It can be configured. CNN can be configured to extract a number of feature components present in an image through a convolutional layer and determine the location and type of an object based on the extracted features.

The parked/stopped vehicle text detection module 123 may be configured to detect text from the license plate detected by the parked/stopped vehicle license plate detection module 122.

Here, the parking/stopped vehicle text detection module 123 uses DNN (Deep Neural Network) technology, and among these, CNN (Convolutional Neural Network), which has excellent performance in object detection in images, is used to detect parked/stopped vehicle text. It may be configured to detect. CNN can be configured to extract a number of feature components present in an image through a convolutional layer and determine the location and type of an object based on the extracted features.

The specifications database 124 for each license plate type may be configured to store in advance specifications regarding the position and number of characters for each license plate type.

The parked/stopped vehicle detection text confirmation module 125 may be configured to check the text detected by the parked/stopped vehicle text detection module 123 by referring to specifications pre-stored in the standard database 124 for each license plate type. Figure 3 illustrates characters detected according to specific predetermined standards.

The empty character position cropping module 126 may be configured to crop the empty character position when all characters are not identified according to the standard in the parked/stopped vehicle detection character confirmation module 125. Figure 4 shows the position of an empty character by cropping it according to a specific predetermined standard. In this case, since it may be an act of intentionally blocking the license plate, partial blocking can be determined by referring to the specific license plate specifications.

The parked/stopped vehicle license plate number recognition module 127 uses the characters confirmed in the parked/stopped vehicle detection character confirmation module 125 when all characters are confirmed according to the standard. It can be configured to recognize the license plate number of a parked/stopped vehicle.

And the parked/stopped vehicle license plate number recognition module 127 determines the empty character position in the empty character position cropping module 126 even if all characters are not confirmed according to the standard in the parked/stopped vehicle detection character confirmation module 125. It can be configured to recognize the number of a parked/stopped vehicle by cropping and recognizing individual characters for each cropped location.

The parked/stopped vehicle control device 130 may be configured to control the parked/stopped vehicle using the license plate number recognized by the parked/stopped vehicle license plate recognition device 120.

The license plate blocking vehicle determination device 140 may be configured to determine whether the parked/stopped vehicle is a license plate blocking vehicle when the vehicle license plate number is not recognized by the parking/stopped vehicle license plate recognition device 120.

The license plate obscuring vehicle discrimination device 140 may be configured to include a vehicle detection box overlap determination module 141, a first license plate obscuring vehicle determination module 142, and a second license plate obscuring vehicle determination module 143. .

Hereinafter, the detailed configuration will be described.

If the license plate of the parked/stopped vehicle is not detected by the parked/stopped vehicle license plate detection module 122, the vehicle detection box overlap determination module 141 detects the parked/stopped vehicle detected by the parked/stopped vehicle detection module 121. It may be configured to determine overlap between vehicle detection boxes of the vehicle.

Figure 5 shows the results of detecting a parked/stopped vehicle in a CCTV video, and the red vehicle box on the right illustrates a state in which the vehicle license plate is obscured due to overlap between vehicle boxes.

If overlap between vehicle detection boxes occurs as a result of the determination of the vehicle detection box overlap determination module 141, the first license plate occluded vehicle determination module 142 detects the vehicle license plate in the parking/stopped vehicle license plate detection module 122. A vehicle that is not parked/stopped may be determined as having its license plate obscured by overlapping vehicles, and if there is no overlap between vehicle boxes but the license plate is not detected, it may be configured to determine it as a vehicle with an intentional license plate occlusion.

The second license plate obscuring vehicle determination module 143 is configured to determine the parked/stopped vehicle as a license plate obscuring vehicle when the number of the parked/stopped vehicle is not recognized in the parked/stopped vehicle license plate recognition module 127. It can be.

The license plate obscuring vehicle occurrence alarm device 150 may be configured to output an alarm regarding the occurrence of a license plate obscuring vehicle when the license plate obscuring vehicle determination device 140 determines that the license plate obscuring vehicle is a vehicle.

FIG. 6 illustrates an electronic display board that outputs a crackdown phrase or guidance phrase in response to an alarm from the license plate blocking vehicle alarm device 150.

Meanwhile, parking/stop enforcement agents can receive alarms through the network and can directly dispatch to the scene to crack down on vehicles that intentionally obscure license plates.

Although the description has been made with reference to the above examples, those skilled in the art can understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. There will be.

110: CCTV device 111: CCTV camera module
112: CCTV video storage module
113: License plate enlargement control module
120: Parking/stopped vehicle license plate recognition device 121: Parking/stopped vehicle detection module
122: Parking/stopped vehicle license plate detection module
123: Parking/stopped vehicle character detection module
124: Standard database for each vehicle license plate type
125: Parking/stopped vehicle detection character confirmation module 126: Empty character location cropping module
127: Parking/stopped vehicle license plate recognition module 130: Parking/stopped vehicle enforcement device
140: License plate blocking vehicle identification device
141: Vehicle detection box overlap judgment module
142: First license plate blocking vehicle identification module
143: 2nd license plate blocking vehicle identification module
150: Alarm device for vehicle license plate blocking

Claims (7)

CCTV device 110 that generates CCTV images;
a parked/stopped vehicle license plate recognition device 120 that recognizes the license plate number of a parked/stopped vehicle from the CCTV image generated by the CCTV device 110;
A parking/stopped vehicle control device 130 that controls the parked/stopped vehicle using the license plate number recognized by the parked/stopped vehicle license plate recognition device 120;
When the license plate number recognition device 120 of the parked/stopped vehicle does not recognize the license plate number, it includes a license plate blocking vehicle determination device 140 that determines whether the parked/stopped vehicle is a vehicle with a license plate cover,
When the vehicle is determined to be a license plate occluded vehicle by the license plate occluded vehicle identification device 140, it further includes a license plate occluded vehicle occurrence alarm device 150 that outputs an alarm regarding the occurrence of a license plate occluded vehicle,
The CCTV device 110,
A CCTV camera module 111 that generates CCTV images of the parked/stopped vehicle and its license plate,
A CCTV image storage module 112 in which CCTV images generated by the CCTV camera module 111 are stored,
When a parked/stopped vehicle is detected in the CCTV image, it includes a license plate enlargement control module 113 that controls the CCTV camera module 111 to enlarge and capture the license plate of the vehicle,
The parking/stopped vehicle license plate number recognition device 120,
A parked/stopped vehicle detection module 121 that detects parked/stopped vehicles in the CCTV image,
It includes a parked/stopped vehicle license plate detection module 122 that detects the license plate of the parked/stopped vehicle detected by the parked/stopped vehicle detection module 121,
The license plate blocking vehicle identification device 140,
If the license plate of the parked/stopped vehicle is not detected by the parked/stopped vehicle license plate detection module 122, the overlap between the vehicle detection boxes of the parked/stopped vehicle detected by the parked/stopped vehicle detection module 121 is A vehicle detection box overlap determination module 141,
If overlap between vehicle detection boxes occurs as a result of the determination of the vehicle detection box overlap determination module 141, the parked/stopped vehicle whose license plate is not detected by the parked/stopped vehicle license plate detection module 122 is detected by the vehicle. It includes a first license plate occlusion vehicle determination module 142 that determines that the vehicle license plate is occluded and, if there is no overlap of vehicles but the vehicle license plate is not detected, determines that the vehicle license plate is intentionally occluded;
The parking/stopped vehicle license plate number recognition device 120,
A parked/stopped vehicle character detection module 123 that detects characters from the vehicle license plate detected by the parked/stopped vehicle license plate detection module 122,
A standard database for each license plate type (124) in which specifications for the position and number of characters for each license plate type are stored in advance;
A parked/stopped vehicle detection text confirmation module 125 that checks the text detected by the parked/stopped vehicle text detection module 123 by referring to specifications pre-stored in the license plate type specification database 124;
An empty character position cropping module 126 that crops empty character positions when all characters are not confirmed according to the standard in the parked/stopped vehicle detection character confirmation module 125;
If all characters are confirmed according to the standard in the parked/stopped vehicle detection text confirmation module 125, the license plate number of the parked/stopped vehicle is recognized using the characters confirmed in the parked/stopped vehicle detection text confirmation module 125. Alternatively, if all the characters are not confirmed according to the standard in the parking/stopped vehicle detection character confirmation module 125, the empty character position cropping module 126 crops the empty character positions and individual characters for each cropped position. It further includes a parked/stopped vehicle license plate number recognition module 127 that recognizes the number of the parked/stopped vehicle,
The license plate enlargement control module 113 controls the CCTV camera module 111 to capture parked/stopped vehicles using PTZ (pan/tilt/zoom) functions and enlarges and captures the license plate,
The parked/stopped vehicle detection module 121 detects the parked/stopped vehicle using CNN (Convolutional Neural Network),
The parking/stopped vehicle license plate detection module 122 detects license plates using CNN (Convolutional Neural Network),
The parked/stopped vehicle text detection module 123 is an illegal parking enforcement system capable of determining intentional license plate blocking, characterized in that it detects parked/stopped vehicle text using a CNN (Convolutional Neural Network).
delete delete delete delete delete According to claim 1,
The license plate blocking vehicle identification device 140,
If the number of the parked/stopped vehicle is not recognized in the parked/stopped vehicle license plate recognition module 127, a second license plate obscuring vehicle determination module 143 is installed to determine the parked/stopped vehicle as a license plate obscuring vehicle. An illegal parking enforcement system capable of determining intentional vehicle license plate blocking, characterized in that it is configured to include more.