CN117456481A - Anti-fake license plate recognition method, system and terminal - Google Patents
Anti-fake license plate recognition method, system and terminal Download PDFInfo
- Publication number
- CN117456481A CN117456481A CN202311777953.4A CN202311777953A CN117456481A CN 117456481 A CN117456481 A CN 117456481A CN 202311777953 A CN202311777953 A CN 202311777953A CN 117456481 A CN117456481 A CN 117456481A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- license plate
- information
- video stream
- position information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 230000004888 barrier function Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000013075 data extraction Methods 0.000 claims description 5
- 238000010191 image analysis Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 14
- 230000006399 behavior Effects 0.000 description 13
- 238000004458 analytical method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000012015 optical character recognition Methods 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Abstract
The application discloses an anti-fake license plate recognition method, a system and a terminal, wherein the method comprises the following steps: acquiring video stream information of a camera and transmitting the video stream information to a vehicle information identification model so as to identify and compare vehicle position information and license plate position information in the video stream information, and carrying out anti-shake detection on license plate information when the license plate position information is confirmed to be in front of the vehicle position information; after license plate number information passes through anti-shake detection, frame difference data of video stream information is obtained, and the frame difference data is imported into a frame difference recognition model for recognition; when the continuous frame number of the same license plate number is recognized to be larger than the first preset continuous frame number, allowing the vehicle to drive in, and judging the moving direction of the vehicle; if the vehicle is identified to travel in the backward direction, the brake is closed, and if the vehicle is identified to travel in the forward direction, the brake is closed after the vehicle passes. According to the method and the device, the continuous video stream is processed or the dynamic behavior of the vehicle is monitored, the image analysis is carried out, the identification accuracy of the anti-fake license plate is enhanced, and the safety of the system is improved.
Description
Technical Field
The present disclosure relates to the field of license plate recognition technologies, and in particular, to an anti-counterfeit license plate recognition method, system, terminal, and computer readable storage medium.
Background
In recent years, vehicle identification systems have become increasingly important in the fields of parking management and road monitoring. In particular, license plate recognition technology, which has been widely used in barrier gate systems to automate vehicle entry management.
In the prior art, license plate recognition systems typically extract license plate information from captured images, typically based on optical character recognition (OCR, optical Character Recognition) technology, to identify and parse characters on the license plate. However, such systems are often limited in their ability to process only static images or to capture images quickly as the vehicle passes, and are not effective in processing continuous video streams or monitoring the dynamic behavior of the vehicle. In addition, there are also operational behavior recognition deficiencies, such as counterfeit image spoofing systems, which may reverse when one vehicle is identified and passes through a gate, allowing another unauthorized vehicle to pass, bypassing the recognition of the system, rendering the monitoring ineffective, since they only perform a single license plate recognition when the vehicle is driving in, the system is generally unable to recognize and prevent such behavior as the vehicle reversing after passing through the gate to let other vehicles pass; in addition, the phenomenon of image deception is easy to occur, the phenomenon of using a printed license plate image deception camera causes that an illegal vehicle is not registered to enter, and due to lack of a deep image analysis mechanism, a real license plate and an image used for deception cannot be distinguished, so that the system is relatively fragile, and the safety cannot be ensured.
Disclosure of Invention
In view of this, the present application provides an anti-counterfeit license plate recognition method, system, terminal and computer readable storage medium, so as to solve the problems that in the prior art, the license plate recognition technology cannot effectively process continuous video stream or monitor dynamic behavior of a vehicle, and a deep image analysis mechanism is lacking, so that the accuracy of license plate anti-counterfeit recognition is insufficient, and the safety of the system cannot be guaranteed.
The application provides an anti-fake license plate recognition method, which comprises the following steps:
acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information identification model, and outputting vehicle position information and license plate position information in the video stream information;
after recognizing that the vehicle position information and the license plate position information exist in the video stream information, comparing the vehicle position information and the license plate position information;
when the license plate position information is confirmed to be in front of the vehicle position information, license plate number information of the license plate position information is obtained, and anti-shake detection is carried out on the license plate number information;
when the license plate number information passes through the anti-shake detection, acquiring frame difference data of the video stream information, and inputting the frame difference data into a frame difference recognition model for recognition;
When the frame difference identification model identifies that the continuous frame number of the same license plate number is larger than a first preset continuous frame number, opening a gate to allow a vehicle to drive in, carrying out target tracking on the vehicle, and judging the moving direction of the vehicle;
and if the vehicle is identified to travel in the backward direction, canceling license plate information record of the vehicle and closing the brake, and if the vehicle is identified to travel in the forward direction, closing the brake after the vehicle travels.
Optionally, the acquiring the video stream information of the camera in real time, inputting the video stream information into a vehicle information identification model, and outputting the vehicle position information and license plate position information in the video stream information, and before the step of further comprising:
and shooting video stream information of the vehicle entering the barrier gate by using a camera, transmitting the video stream information to a display user interface, and communicating with the barrier gate through the display user interface.
Optionally, the acquiring video stream information of the camera in real time, inputting the video stream information into a vehicle information identification model, and outputting vehicle position information and license plate position information in the video stream information specifically includes:
acquiring video stream information of a camera in real time, and detecting and identifying the video stream information by adopting a target detection algorithm and a license plate identification algorithm;
And obtaining the optical characters of the vehicle, the license plate and the license plate number in the video stream information according to the detection and the identification result.
Optionally, the acquiring the video stream information of the camera in real time, inputting the video stream information into a vehicle information identification model, and outputting the vehicle position information and license plate position information in the video stream information, and then further includes:
judging whether a vehicle and a license plate exist in a database, if so, judging whether the license plate position information is in front of the vehicle position information; if not, returning to acquire the video stream information of the camera in real time.
Optionally, the acquiring the frame difference data of the video stream information, and inputting the frame difference data into a frame difference recognition model for recognition specifically includes:
acquiring a first frame image and a second frame image from the video stream information, and comparing the difference between the first frame image and the second frame image to obtain the frame difference data;
wherein the frame difference data comprises an image difference area, an x coordinate of an average centroid position of the image difference area, a y coordinate of an average centroid position of the image difference area, an average moving direction of the image and an average moving speed of the image;
Recording the frame difference data to a data group, and keeping updating the data group within a first preset time;
and calling all the frame difference data in the data set, and inputting all the frame difference data into a frame difference identification model for identification.
Optionally, the inputting the frame difference data into a frame difference recognition model for recognition further includes:
extracting first video frame difference data of all videos of the vehicle driving into the view range of the lens to form a first data set;
performing second video frame difference data extraction on all videos with photos in front of the lens to form a second data set;
and performing model training by using the first data set and the second data set to generate the frame difference identification model.
Optionally, the target tracking is performed on the vehicle, and the moving direction of the vehicle is determined, which specifically includes:
tracking the vehicle by adopting a target tracking algorithm;
and distinguishing the forward and backward of the vehicle by tracking the centroid position of the vehicle, and judging the moving direction of the vehicle according to the change of the centroid position.
The application also provides an anti-fake license plate recognition system, anti-fake license plate recognition system includes:
The vehicle information acquisition module is used for acquiring video stream information of the camera in real time, inputting the video stream information into the vehicle information identification model and outputting vehicle position information and license plate position information in the video stream information;
the vehicle information comparison module is used for comparing the vehicle position information with the license plate position information after recognizing that the vehicle position information and the license plate position information exist in the video stream information;
the vehicle anti-shake detection module is used for acquiring license plate number information of the license plate position information when confirming that the license plate position information is in front of the vehicle position information, and carrying out anti-shake detection on the license plate number information;
the frame difference data identification module is used for acquiring frame difference data of the video stream information after the license plate number information passes the anti-shake detection, and inputting the frame difference data into a frame difference identification model for identification;
the vehicle entrance judging module is used for opening a gate to allow a vehicle to enter when the frame difference recognition model recognizes that the continuous frame number of the same license plate number is larger than a first preset continuous frame number, carrying out target tracking on the vehicle and judging the moving direction of the vehicle;
And the vehicle driving-out judging module is used for canceling license plate information record of the vehicle and closing the brake if the vehicle is identified to travel in the backward direction, and closing the brake after the vehicle is identified to travel in the forward direction.
The application also proposes a terminal, the terminal includes: the anti-fake license plate recognition system comprises a processor, a memory and an anti-fake license plate recognition program which is stored in the memory and can run on the processor, wherein the anti-fake license plate recognition program realizes the steps of the anti-fake license plate recognition method when being executed by the processor.
The application also provides a computer readable storage medium, wherein the computer readable storage medium stores an anti-fake license plate recognition program, and the anti-fake license plate recognition program realizes the steps of the anti-fake license plate recognition method when being executed by a processor.
The beneficial effects of this application are: compared with the prior art, the method and the device have the advantages that the video stream information of the camera is obtained in real time, the video stream information is transmitted to the vehicle information identification model to identify the vehicle position information and the license plate position information in the video stream information, and after the vehicle position information and the license plate position information in the video stream information are detected, the vehicle position information and the license plate position information are compared, so that the relation between the dynamic license plate position information and the vehicle position information is better confirmed, and the identification accuracy is improved; secondly, acquiring license plate number information of license plate position information by judging that the license plate position information is in front of the vehicle position information, performing anti-shake detection on the license plate number information to prevent the use of a photo of a vehicle for identification, acquiring frame difference data of video stream information after the license plate number information passes through the anti-shake detection, importing the frame difference data into a frame difference identification model for identification, and performing deep analysis on the image; and if the vehicle is identified to travel in the backward direction, the license plate information record of the vehicle is withdrawn, and the vehicle is closed after the vehicle travels in the forward direction, the continuous video stream can be effectively processed, the dynamic behavior of the vehicle is monitored, photo vehicles are avoided through the frame difference data co-accumulation anti-shake detection, the traveling direction of the vehicle after the opening is also avoided, the identified vehicle is prevented from opening the gate for other vehicles, the vehicle identification is enhanced, and the system safety is increased.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a preferred embodiment of the anti-counterfeit license plate recognition method of the present application;
FIG. 2 is an overall flow chart of the anti-counterfeit license plate recognition method of the present application;
FIG. 3 is a user interface diagram of the anti-counterfeit license plate recognition method of the present application;
FIG. 4 is a flow chart of frame difference analysis of the anti-counterfeit license plate recognition method of the present application;
FIG. 5 is a schematic diagram of an identification picture of the anti-counterfeit license plate identification method of the present application;
FIG. 6 is a schematic diagram of a preferred embodiment of the anti-counterfeit license plate recognition system of the present application;
FIG. 7 is a schematic diagram of an operating environment of a preferred embodiment of the terminal of the present application.
Detailed Description
In order to better understand the technical solutions of the present application, the anti-counterfeit license plate recognition method, system, terminal and computer readable storage medium provided in the present application are described in further detail below with reference to the accompanying drawings and detailed description. It is to be understood that the described embodiments are merely some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms "first," "second," and the like in this application are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The application provides an anti-fake license plate recognition method, an anti-fake license plate recognition system, a terminal and a computer readable storage medium, which are used for solving the problems that in the prior art, a license plate recognition technology cannot effectively process continuous video streams or monitor dynamic behaviors of vehicles, and an in-depth image analysis mechanism is lacked, so that the anti-fake license plate recognition accuracy is insufficient, and the system safety cannot be guaranteed.
Referring to fig. 1 to 5, fig. 1 is a flowchart of a preferred embodiment of the anti-counterfeit license plate recognition method of the present application; FIG. 2 is an overall flow chart of the anti-counterfeit license plate recognition method of the present application; FIG. 3 is a user interface diagram of the anti-counterfeit license plate recognition method of the present application; FIG. 4 is a flow chart of frame difference analysis of the anti-counterfeit license plate recognition method of the present application; fig. 5 is a schematic diagram of an identification picture of the anti-counterfeit license plate identification method of the present application.
The application provides an anti-fake license plate recognition method, wherein the anti-fake license plate recognition method comprises the following steps of:
step S100: and acquiring video stream information of the camera in real time, inputting the video stream information into a vehicle information identification model, and outputting vehicle position information and license plate position information in the video stream information.
Specifically, the video stream information of the camera is obtained in real time, various conditions can be responded immediately, such as immediately identifying suspicious vehicles, so that necessary safety measures are timely taken, the video stream information is transmitted to the vehicle information identification model, the vehicle position information and license plate position information in the video stream information can be identified more accurately, the data processing is more efficient and intelligent, the license plate identification accuracy is improved, the identification capability of the whole system for forging or falsifying license plates is also enhanced, and the safety of the vehicle management and monitoring system is improved.
Wherein, the step S100: acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information identification model, and outputting vehicle position information and license plate position information in the video stream information, wherein the method comprises the following steps: and shooting video stream information of the vehicle entering the barrier gate by using a camera, transmitting the video stream information to a display user interface, and communicating with the barrier gate through the display user interface.
Specifically, the camera is used for shooting video stream information of vehicles entering the barrier gate, the video stream information is transmitted to the display user interface, as shown in fig. 3, an operator or a system user can monitor the condition of each vehicle in real time, the visualization method provides instant feedback, the intuitiveness and the effectiveness of vehicle monitoring are enhanced, the display user interface is connected with the communication of the barrier gate, an integrated system is realized, the operation flow is simplified, and the convenience of operation and the reliability of the system are enhanced.
The design of the user interface can be completed by adopting a tkilter module, as shown in fig. 2, and the interface comprises a video stream image acquired by a camera, current license plate and moving direction information of a vehicle, already-recorded license plate information, and keys for manually controlling a barrier switch and manually clearing information, and when a rectangular box flow appears in fig. 2, target tracking is started.
Wherein, the step S100: acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information identification model, and outputting vehicle position information and license plate position information in the video stream information, wherein the method specifically comprises the following steps of:
Acquiring video stream information of a camera in real time, and detecting and identifying the video stream information by adopting a target detection algorithm and a license plate identification algorithm;
and obtaining the optical characters of the vehicle, the license plate and the license plate number in the video stream information according to the detection and the identification result.
Specifically, the video stream information of the camera is obtained in real time, the target detection algorithm and the license plate recognition algorithm are adopted for the video stream information, and the optical characters of the vehicle, the license plate and the license plate number in the video stream information can be accurately recognized, so that the system can effectively distinguish the real license plate from the fake license plate, the reliability and the effectiveness of the whole license plate management system are enhanced, the recognition errors can be reduced by utilizing the optical characters of the license plate and the license plate number, and the accuracy and the efficiency of license plate recognition are improved.
The target detection algorithm can adopt a yolov5 network model, the license plate recognition algorithm can adopt an LPRnet network model, namely, the basic functions of license plate recognition, namely, the recognition of vehicles and license plates and the recognition of optical characters of license plates are completed by using a mode of combining the yolov5 network model and the LPRnet network model.
Wherein, the step S100: acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information identification model, and outputting vehicle position information and license plate position information in the video stream information, wherein the method comprises the following steps:
Judging whether a vehicle and a license plate exist in a database, if so, judging whether the license plate position information is in front of the vehicle position information; if not, returning to acquire the video stream information of the camera in real time.
Specifically, whether a vehicle and a license plate exist in a database or not is judged, if yes, whether the license plate position information is in front of the vehicle position information is judged, error recognition is prevented, fraudulent conduct is prevented, if fake license plates or license plates which do not accord with the vehicle are used, if not, video stream information of a camera is acquired in real time, and a real-time verification and response mechanism ensures that a system can process new or unknown vehicles in time, so that response speed and efficiency of the whole recognition system are improved.
Step S200: and comparing the vehicle position information with the license plate position information after recognizing that the vehicle position information and the license plate position information exist in the video stream information.
Specifically, after detecting that the vehicle position information and the license plate position information exist in the video stream information, the vehicle position information and the license plate position information are compared, so that the fact that the identified license plate belongs to the corresponding vehicle can be effectively ensured, and an accurate matching mechanism is beneficial to reducing false identification.
Step S300: and when the license plate position information is confirmed to be in front of the vehicle position information, license plate number information of the license plate position information is acquired, and anti-shake detection is carried out on the license plate number information.
Specifically, when license plate position information is confirmed to be in front of the vehicle position information, license plate number information of the license plate position information is obtained, in order to enhance anti-interference capability, relative position recognition and anti-shake functions are added, anti-shake detection is performed on the license plate number information, image instability caused by camera shake, vehicle movement or other external factors can be filtered, and whether a real vehicle or a photo vehicle is identified.
The relative position recognition can be performed by adopting a small model formed by a full-connection layer, and the relative position relation between the license plate and the vehicle is obtained by acquiring the coordinate position information of the license plate and the vehicle, so that the interference of the license plate or suspected license plate which is not positioned right in front of the vehicle on the recognition is eliminated. In addition, the anti-shake function can also buffer the identified license plate numbers, and the license plate numbers can be recorded when the same license plate numbers are continuously read for a plurality of times, so that the anti-interference performance of the whole model is enhanced, and the accuracy of the character identification of the license plate numbers is improved.
Step S400: and when the license plate number information passes through the anti-shake detection, acquiring frame difference data of the video stream information, and inputting the frame difference data into a frame difference recognition model for recognition.
Specifically, after the license plate number information is subjected to anti-shake detection, frame difference data of the video stream information is obtained, the frame difference data is imported into a frame difference recognition model for recognition, the frame difference data can reveal fine changes of license plate images among continuous frames, the license plate identification method is beneficial to distinguishing real license plates from possible fake or falsified license plates, and stability, accuracy and safety of license plate recognition are effectively improved.
The step S400: when the license plate number information passes through the anti-shake detection, acquiring frame difference data of the video stream information, and inputting the frame difference data into a frame difference recognition model for recognition, wherein the method specifically comprises the following steps of:
acquiring a first frame image and a second frame image from the video stream information, and comparing the difference between the first frame image and the second frame image to obtain the frame difference data;
wherein the frame difference data comprises an image difference area, an x coordinate of an average centroid position of the image difference area, a y coordinate of an average centroid position of the image difference area, an average moving direction of the image and an average moving speed of the image;
recording the frame difference data to a data group, and keeping updating the data group within a first preset time;
And calling all the frame difference data in the data set, and inputting all the frame difference data into a frame difference identification model for identification.
Specifically, a first frame image and a second frame image are obtained from video stream information, differences of the second frame image and the first frame image are compared, and frame difference data are obtained, wherein the frame difference data comprise an image difference area, an x coordinate of an average centroid position of the image difference area, a y coordinate of an average centroid position of the image difference area, an average moving direction of the image and an average moving speed of the image, and dynamic changes of a vehicle and a license plate can be effectively captured. The dynamic analysis capability is not possessed by the traditional static license plate recognition method, can provide more information about the behavior and state of the vehicle, records the frame difference data into a data set, keeps updating the data set within a first preset time, retrieves all the frame difference data in the data set, and guides all the frame difference data into a frame difference recognition model for recognition, wherein in the dynamic behavior of the vehicle, license plates which show abnormal or inconsistent dynamic characteristics in continuous frames, such as fake or tampered license plates, can be recognized. The long-term data analysis can provide more comprehensive information than single frame analysis, and is helpful for improving the accuracy of identifying fake license plates.
The first preset time may be set to 3s, or may be set to other time intervals as required.
Wherein, the steps are as follows: inputting the frame difference data into a frame difference identification model for identification, wherein the method comprises the following steps:
extracting first video frame difference data of all videos of the vehicle driving into the view range of the lens to form a first data set;
performing second video frame difference data extraction on all videos with photos in front of the lens to form a second data set;
and performing model training by using the first data set and the second data set, generating the frame difference identification model, and importing all the frame difference data into the frame difference identification model for identification.
Specifically, a first video frame difference data extraction is performed on all videos of a vehicle driving into a lens visual field range to form a first data set, a second video frame difference data extraction is performed on all videos of a photo placed in front of the lens to form a second data set, model training is performed by using the first data set and the second data set to generate a frame difference recognition model, and all frame difference data are imported into the frame difference recognition model for recognition.
That is, the present application adopts a method of frame difference analysis in the resolution of distinguishing the real license plate from the picture for fraud, and the conventional license plate recognition program cannot distinguish whether the real vehicle appears in front of the lens or whether the picture of the vehicle is artificially placed in front of the lens, and can make the system enter the wrong license plate number by artificially blocking the lens with the picture. The present application addresses this problem according to the dynamic differences that exist in the process of a vehicle driving into the field of view of the lens and a photograph being placed into the field of view of the lens.
Specifically, the pixel change is always in a fixed local area in the process of driving into the lens, the direction of the pixel change is stable and smooth, the pixels of the whole picture are always changed in the process of manually placing the picture in front of the lens, and the hand-held picture or the mobile phone and the like are dithered, so that the picture can be distinguished according to the pixel change in the video stream before the license plate is identified. Firstly, sampling frames in a video stream, comparing images of the front frame and the rear frame, obtaining pixel difference information, recording an image difference area between the frames, an x coordinate and a y coordinate of a difference average centroid position, an average moving direction and an average moving speed of 5 data, storing the data as 0 if the images of the front frame and the rear frame are consistent, continuously updating and storing the difference information recorded by each frame in the last three seconds by a system, and forming a data group (for example, storing 150 data if 10 frames per second) on a time sequence with the data quantity of frame number of 5. After the license plate is identified, an instruction is sent to call the stored data set, the data set is input into a trained machine learning model to infer, and whether the identified license plate is from a real vehicle or a vehicle on a photo is distinguished.
The frame difference recognition model is composed of a plurality of full-connection layers, a batch standardization layer and a random discarding layer, and comprises data acquisition, model training and model reasoning program files corresponding to the model, namely, a data set is formed by extracting data from videos of a large number of vehicles driving into the view range of a lens and videos of the photos placed in front of the lens, and the model is subjected to supervised learning, so that the capability of distinguishing the real vehicles from the photos of the vehicles is obtained. As shown in fig. 4, a flowchart is formed for a frame difference recognition model, as shown in fig. 5, and in order to distinguish photo examples, the lower left corner prompts that "there is an abnormal record," please reverse to reenter "and no license plate number is entered and no brake is opened when an abnormal vehicle is recognized. The traditional picture recognition scheme mainly comprises static recognition, and is characterized in that planes such as vehicles, pictures and the like are distinguished in a mode such as active light source reflectivity and the like, so that the requirement on algorithm accuracy is high, and the requirement on calculation force is high. The scheme adopts time sequence data, simplifies video stream data into image difference data, distinguishes by distinguishing the moving position, shaking and the like of the vehicle before the vehicle is driven in and the picture is put into the lens, has relatively less required processing data quantity and dynamically utilizes the video stream data.
The method can also adjust the frame sampling frequency, change the data sampling information, change the acquisition parameters of the difference analysis, for example, change the average difference into the mass center, the moving direction and the speed of the area with the largest difference pixels, and increase related data such as the mass center moving path, the difference contour range, the difference contour perimeter, the shape and the like, so as to improve the accuracy rate and the like. The frame sampling frequency and the comparison mode can be changed, the current comparison mode is that each frame is compared with the previous frame, or the comparison among multi-frame images or the comparison between each frame of image and the first frame of image are changed, the comparison is carried out every other frames, the difference value is improved, and the like. The current frame difference recognition model consists of a full connection layer, a batch standardization layer and a random discarding layer, and a normalization layer, a convolution layer and the like can be further added, or data similar to the scheme can be acquired by adopting modes of target tracking and the like for training, such as acquiring a centroid path of a moving object by adopting an optical flow method for training and the like.
Step S500: when the frame difference identification model identifies that the continuous frame number of the same license plate number is larger than the first preset continuous frame number, opening a gate to allow a vehicle to drive in, carrying out target tracking on the vehicle, and judging the moving direction of the vehicle.
Specifically, when the frame difference recognition model recognizes that the continuous frame number of the same license plate number is greater than the first preset continuous frame number, the brake is opened to allow the vehicle to drive in, target tracking is performed on the vehicle, and the moving direction of the vehicle is judged, so that the behavior of the vehicle in a specific area can be effectively monitored, and improper behaviors such as retrograde or unauthorized entry can be prevented.
The first preset continuous frame number is set to 5, and may be set to other values as required.
Wherein, the steps are as follows: the method for tracking the target of the vehicle and judging the moving direction of the vehicle specifically comprises the following steps:
tracking the vehicle by adopting a target tracking algorithm;
and distinguishing the forward and backward of the vehicle by tracking the centroid position of the vehicle, and judging the moving direction of the vehicle according to the change of the centroid position.
Specifically, a target tracking algorithm is adopted for the vehicle, the forward movement and the backward movement of the vehicle are distinguished by tracking the centroid position of the vehicle, and the moving direction of the vehicle is judged according to the change of the centroid position, so that the forward movement and the backward movement of the vehicle can be accurately distinguished, and possible safety risks such as wrong driving or reverse driving and the like can be recognized in advance.
The target tracking algorithm can adopt a CSRT tracker in an opencv module to realize target tracking, after the initial position of an image is acquired, the tracker tracks the position of a vehicle in the image, the vehicle is mainly distinguished into forward and backward movements based on a simple barrier gate environment, the forward and backward movements of the vehicle can be distinguished by tracking the change of the centroid position of the vehicle, and when the centroid reaches the boundary position of the image, the vehicle can be confirmed to leave, and different works can be operated according to the leaving position.
The method can also realize the target tracking function by adopting deep SORT, KLT Tracker, GOTURN Tracker and the like, but can select a CSRT Tracker which is more suitable for quick processing and has relatively low calculation power required by performance when only single target tracking is performed and large-area shielding does not exist.
Step S600: and if the vehicle is identified to travel in the backward direction, canceling license plate information record of the vehicle and closing the brake, and if the vehicle is identified to travel in the forward direction, closing the brake after the vehicle travels.
Specifically, if the vehicle is identified to travel in the backward direction, license plate information record of the vehicle is canceled and the brake is closed, if the vehicle is identified to travel in the forward direction, the brake is closed after the vehicle passes, and the unauthorized or wrong vehicle can be effectively prevented from entering.
The communication part of the switch gate can adopt the socket module to realize the communication of the Internet of things so as to realize the switching-on and switching-off of the host end transmission instruction control barrier gate, and also can adopt SIOT communication.
As shown in FIG. 2, the overall workflow diagram shows a user interface on the host side when the system starts to operate, including real-time camera images and license plate information, and also includes some keys to manually intervene in switching gates, and shows user interface connections to communicate with the gates. The camera can firstly transmit video streams to a vehicle and license plate recognition model, frame difference data are stored every 0.1 second and are stored for frame difference analysis, the model can recognize the position of the vehicle and the position of the license plate, when at least one vehicle and one license plate are detected, relative position comparison can be carried out, license plate recognition is carried out after the license plate is confirmed to be right in front of the vehicle, anti-shake detection can be carried out on the license plate recognition, and only when the same license plate is recognized by continuous frames, the data input flow can be entered. When entering the recording process, firstly checking the frame difference data stored before, transmitting the data into a model for comparison, canceling recording and warning if abnormal, entering the next step for comparing whether license plates are repeatedly recorded or not if abnormal, recording a list again after no recording, knowing that a brake is opened through the internet of things, starting to track the automobile, distinguishing the forward and backward movement modes of the automobile by the target tracking, if the forward and backward movement modes leave a picture, normally closing the brake, ending the process, and canceling the recording of the brake, ending the process if the backward movement is away, and waiting for the next license plate recording after the process is finished.
In conclusion, the anti-shake function is added on the basic license plate recognition function, and the anti-interference capability and accuracy of the artificial intelligent model are improved through the small model and the program mode. The object tracking function is added to judge and record the operation behavior of the vehicle, so that the vehicle operation behavior is more strongly monitored, and detection of the vehicle position by other sensors such as infrared ranging is omitted. The method is characterized in that a frame difference analysis mode is adopted to distinguish a vehicle from a picture, so that a real license plate and a deceptive image are distinguished, the deceptive capability of license plate recognition is enhanced, the data information of the image difference area, the average mass center, the average moving direction and the moving speed of a difference area between frames is collected, and the method is different from other recognition modes, wherein the data of pixel differences between the frames of images are taken as analysis data of a model, and the differences of the license plate and the picture of the real vehicle are distinguished from a dynamic time sequence. And dynamic data analysis is carried out on the vehicles after and before the recognition in a target tracking and frame difference analysis mode, so that the stability of the system is enhanced.
Referring to fig. 6 to 7, fig. 6 is a schematic diagram of a preferred embodiment of the anti-counterfeit license plate recognition system of the present application; FIG. 7 is a schematic diagram of an operating environment of a preferred embodiment of the terminal of the present application.
In some embodiments, as shown in fig. 6, based on the above anti-counterfeit license plate recognition method, the present application further provides an anti-counterfeit license plate recognition system, where the anti-counterfeit license plate recognition system includes:
the vehicle information acquisition module 51 is configured to acquire video stream information of a camera in real time, input the video stream information into a vehicle information identification model, and output vehicle position information and license plate position information in the video stream information;
the vehicle information comparing module 52 is configured to compare the vehicle position information and the license plate position information after recognizing that the vehicle position information and the license plate position information exist in the video stream information;
the vehicle anti-shake detection module 53 is configured to obtain license plate number information of the license plate position information when it is confirmed that the license plate position information is in front of the vehicle position information, and perform anti-shake detection on the license plate number information;
the frame difference data identification module 54 is configured to obtain frame difference data of the video stream information after the license plate number information passes the anti-shake detection, and input the frame difference data into a frame difference identification model for identification;
a vehicle entrance judgment module 55, configured to, when the frame difference recognition model recognizes that the number of continuous frames of the same license plate number is greater than a first preset number of continuous frames, open a gate to allow a vehicle to enter, perform target tracking on the vehicle, and judge a moving direction of the vehicle;
The vehicle exit judging module 56 is configured to cancel the license plate information record of the vehicle and close the brake if the vehicle is identified to travel in the backward direction, and close the brake after the vehicle is identified to travel in the forward direction.
In some embodiments, as shown in fig. 7, based on the above anti-counterfeit license plate recognition method and system, the present application further provides a terminal correspondingly, where the terminal includes: the processor 10, memory 20, display 30, fig. 7 only show some of the components of the terminal, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead.
The memory 20 may in some embodiments be an internal storage unit of the terminal, such as a hard disk or a memory of the terminal. The memory 20 may in other embodiments also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal. Further, the memory 20 may also include both an internal storage unit and an external storage device of the terminal. The memory 20 is used for storing application software installed in the terminal and various data, such as program codes of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output.
In an embodiment, the memory 20 stores an anti-counterfeit license plate recognition program 40, and the anti-counterfeit license plate recognition program 40 can be executed by the processor 10, so as to implement the anti-counterfeit license plate recognition method in the present application.
The processor 10 may be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip in some embodiments, for executing program codes or processing data stored in the memory 20, such as executing the anti-counterfeit license plate recognition method.
The display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like in some embodiments. The display 30 is used for displaying information at the terminal and for displaying a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.
The application also provides a computer readable storage medium, wherein the computer readable storage medium stores an anti-fake license plate recognition program, and the anti-fake license plate recognition program realizes the steps of the anti-fake license plate recognition method when being executed by a processor.
In summary, the video stream information of the camera is obtained in real time, the video stream information is transmitted to the vehicle information identification model to identify the vehicle position information and the license plate position information in the video stream information, and after the vehicle position information and the license plate position information in the video stream information are detected, the vehicle position information and the license plate position information are compared to better confirm the relation between the dynamic license plate position information and the vehicle position information, so that the identification accuracy is improved; secondly, acquiring license plate number information of license plate position information by judging that the license plate position information is in front of the vehicle position information, performing anti-shake detection on the license plate number information to prevent the use of a photo of a vehicle for identification, acquiring frame difference data of video stream information after the license plate number information passes through the anti-shake detection, importing the frame difference data into a frame difference identification model for identification, and performing deep analysis on the image; and if the vehicle is identified to travel in the backward direction, the license plate information record of the vehicle is withdrawn, and the vehicle is closed after the vehicle travels in the forward direction, the continuous video stream can be effectively processed, the dynamic behavior of the vehicle is monitored, photo vehicles are avoided through the frame difference data co-accumulation anti-shake detection, the traveling direction of the vehicle after the opening is also avoided, the identified vehicle is prevented from opening the gate for other vehicles, the vehicle identification is enhanced, and the system safety is increased.
It should be noted that, the various optional implementations described in the embodiments of the present application may be implemented in combination with each other, or may be implemented separately, which is not limited to the embodiments of the present application.
In the description of the present application, it should be understood that the terms "upper," "lower," "left," "right," and the like indicate an orientation or a positional relationship based on that shown in the drawings, and are merely for convenience of description of the present application and for simplification of the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, as well as a specific orientation configuration and operation. Therefore, it is not to be construed as limiting the present application. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of the present application, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art in a specific context.
The embodiments described above are described with reference to the drawings, and other different forms and embodiments are possible without departing from the principles of the present application, and thus the present application should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will convey the scope of the application to those skilled in the art. In the drawings, component dimensions and relative dimensions may be exaggerated for clarity. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. The terms "comprises," "comprising," and/or "includes," when used in this specification, specify the presence of stated features, integers, components, and/or groups thereof, but do not preclude the presence or addition of one or more other features, integers, components, and/or groups thereof. Unless otherwise indicated, numerical ranges are stated to include the upper and lower limits of the range and any subranges therebetween.
The foregoing description is only a partial embodiment of the present application, and is not intended to limit the scope of the present application, and all equivalent devices or equivalent process transformations made by using the descriptions and the drawings of the present application, or direct or indirect application to other related technical fields, are included in the patent protection scope of the present application.
Claims (10)
1. The anti-fake license plate recognition method is characterized by comprising the following steps of:
acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information identification model, and outputting vehicle position information and license plate position information in the video stream information;
after recognizing that the vehicle position information and the license plate position information exist in the video stream information, comparing the vehicle position information and the license plate position information;
when the license plate position information is confirmed to be in front of the vehicle position information, license plate number information of the license plate position information is obtained, and anti-shake detection is carried out on the license plate number information;
when the license plate number information passes through the anti-shake detection, acquiring frame difference data of the video stream information, and inputting the frame difference data into a frame difference recognition model for recognition;
when the frame difference identification model identifies that the continuous frame number of the same license plate number is larger than a first preset continuous frame number, opening a gate to allow a vehicle to drive in, carrying out target tracking on the vehicle, and judging the moving direction of the vehicle;
and if the vehicle is identified to travel in the backward direction, canceling license plate information record of the vehicle and closing the brake, and if the vehicle is identified to travel in the forward direction, closing the brake after the vehicle travels.
2. The anti-counterfeit license plate recognition method according to claim 1, wherein the acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information recognition model, and outputting vehicle position information and license plate position information in the video stream information, further comprises:
and shooting video stream information of the vehicle entering the barrier gate by using a camera, transmitting the video stream information to a display user interface, and communicating with the barrier gate through the display user interface.
3. The anti-counterfeiting license plate recognition method according to claim 1, wherein the acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information recognition model, and outputting vehicle position information and license plate position information in the video stream information specifically comprises:
acquiring video stream information of a camera in real time, and detecting and identifying the video stream information by adopting a target detection algorithm and a license plate identification algorithm;
and obtaining the optical characters of the vehicle, the license plate and the license plate number in the video stream information according to the detection and the identification result.
4. The anti-counterfeit license plate recognition method according to claim 1, wherein the acquiring video stream information of a camera in real time, inputting the video stream information into a vehicle information recognition model, outputting vehicle position information and license plate position information in the video stream information, and further comprises:
Judging whether a vehicle and a license plate exist in a database, if so, judging whether the license plate position information is in front of the vehicle position information; if not, returning to acquire the video stream information of the camera in real time.
5. The anti-counterfeit license plate recognition method according to claim 1, wherein the acquiring the frame difference data of the video stream information, inputting the frame difference data into a frame difference recognition model for recognition, comprises the following steps:
acquiring a first frame image and a second frame image from the video stream information, and comparing the difference between the first frame image and the second frame image to obtain the frame difference data;
wherein the frame difference data comprises an image difference area, an x coordinate of an average centroid position of the image difference area, a y coordinate of an average centroid position of the image difference area, an average moving direction of the image and an average moving speed of the image;
recording the frame difference data to a data group, and keeping updating the data group within a first preset time;
and calling all the frame difference data in the data set, and inputting all the frame difference data into a frame difference identification model for identification.
6. The method for recognizing an anti-counterfeit license plate according to claim 5, wherein the step of inputting the frame difference data into a frame difference recognition model for recognition further comprises:
Extracting first video frame difference data of all videos of the vehicle driving into the view range of the lens to form a first data set;
performing second video frame difference data extraction on all videos with photos in front of the lens to form a second data set;
and performing model training by using the first data set and the second data set to generate the frame difference identification model.
7. The method for recognizing an anti-counterfeit license plate according to claim 1, wherein the steps of performing object tracking on the vehicle and judging a moving direction of the vehicle include:
tracking the vehicle by adopting a target tracking algorithm;
and distinguishing the forward and backward of the vehicle by tracking the centroid position of the vehicle, and judging the moving direction of the vehicle according to the change of the centroid position.
8. An anti-counterfeiting license plate recognition system, characterized in that the anti-counterfeiting license plate recognition system comprises:
the vehicle information acquisition module is used for acquiring video stream information of the camera in real time, inputting the video stream information into the vehicle information identification model and outputting vehicle position information and license plate position information in the video stream information;
the vehicle information comparison module is used for comparing the vehicle position information with the license plate position information after recognizing that the vehicle position information and the license plate position information exist in the video stream information;
The vehicle anti-shake detection module is used for acquiring license plate number information of the license plate position information when confirming that the license plate position information is in front of the vehicle position information, and carrying out anti-shake detection on the license plate number information;
the frame difference data identification module is used for acquiring frame difference data of the video stream information after the license plate number information passes the anti-shake detection, and inputting the frame difference data into a frame difference identification model for identification;
the vehicle entrance judging module is used for opening a gate to allow a vehicle to enter when the frame difference recognition model recognizes that the continuous frame number of the same license plate number is larger than a first preset continuous frame number, carrying out target tracking on the vehicle and judging the moving direction of the vehicle;
and the vehicle driving-out judging module is used for canceling license plate information record of the vehicle and closing the brake if the vehicle is identified to travel in the backward direction, and closing the brake after the vehicle is identified to travel in the forward direction.
9. A terminal, the terminal comprising: the anti-fake license plate recognition method comprises a processor, a memory and an anti-fake license plate recognition program which is stored in the memory and can run on the processor, wherein the anti-fake license plate recognition program is executed by the processor to realize the steps of the anti-fake license plate recognition method according to any one of claims 1-7.
10. A computer readable storage medium, wherein the computer readable storage medium stores an anti-counterfeit license plate recognition program, which when executed by a processor, implements the steps of the anti-counterfeit license plate recognition method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311777953.4A CN117456481A (en) | 2023-12-22 | 2023-12-22 | Anti-fake license plate recognition method, system and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311777953.4A CN117456481A (en) | 2023-12-22 | 2023-12-22 | Anti-fake license plate recognition method, system and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117456481A true CN117456481A (en) | 2024-01-26 |
Family
ID=89580200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311777953.4A Pending CN117456481A (en) | 2023-12-22 | 2023-12-22 | Anti-fake license plate recognition method, system and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117456481A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108335489A (en) * | 2018-03-11 | 2018-07-27 | 西安电子科技大学 | Vehicle on highway behavior semantic analysis and abnormal behaviour monitoring system and method |
| CN113205069A (en) * | 2021-05-27 | 2021-08-03 | 上海高德威智能交通系统有限公司 | False license plate detection method and device and computer storage medium |
| CN113602264A (en) * | 2021-08-17 | 2021-11-05 | 北京市商汤科技开发有限公司 | Vehicle driving behavior detection method, device, equipment and storage medium |
| CN113920749A (en) * | 2021-09-29 | 2022-01-11 | 深圳市捷顺科技实业股份有限公司 | Vehicle following identification method and system for parking lot and related device |
| KR20220151935A (en) * | 2021-05-07 | 2022-11-15 | 박영세 | System of detecting fake license plates and its method by using the same |
| KR20230009598A (en) * | 2021-07-09 | 2023-01-17 | 주식회사 현대케피코 | Vehicle license plate recognition and counterfeit determination method and system in which the method is performed |
| CN117115801A (en) * | 2023-10-10 | 2023-11-24 | 深圳市捷顺科技实业股份有限公司 | License plate authenticity identification method, device, equipment and storage medium |
-
2023
- 2023-12-22 CN CN202311777953.4A patent/CN117456481A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108335489A (en) * | 2018-03-11 | 2018-07-27 | 西安电子科技大学 | Vehicle on highway behavior semantic analysis and abnormal behaviour monitoring system and method |
| KR20220151935A (en) * | 2021-05-07 | 2022-11-15 | 박영세 | System of detecting fake license plates and its method by using the same |
| CN113205069A (en) * | 2021-05-27 | 2021-08-03 | 上海高德威智能交通系统有限公司 | False license plate detection method and device and computer storage medium |
| KR20230009598A (en) * | 2021-07-09 | 2023-01-17 | 주식회사 현대케피코 | Vehicle license plate recognition and counterfeit determination method and system in which the method is performed |
| CN113602264A (en) * | 2021-08-17 | 2021-11-05 | 北京市商汤科技开发有限公司 | Vehicle driving behavior detection method, device, equipment and storage medium |
| CN113920749A (en) * | 2021-09-29 | 2022-01-11 | 深圳市捷顺科技实业股份有限公司 | Vehicle following identification method and system for parking lot and related device |
| CN117115801A (en) * | 2023-10-10 | 2023-11-24 | 深圳市捷顺科技实业股份有限公司 | License plate authenticity identification method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘爽: "智能车辆出入控制系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 12, 15 December 2013 (2013-12-15), pages 140 - 120 * |
| 周芳芹 等: "基于Matlab的真伪车牌识别系统的研究", 《科技创新与应用》, no. 11, 20 April 2018 (2018-04-20), pages 50 - 51 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106652551B (en) | Parking space detection method and equipment | |
| CN102833478B (en) | Fault-tolerant background model | |
| CN105336170B (en) | Traffic violation supervising method and its device | |
| CN110163100B (en) | Anti-photographing display | |
| CN105654733A (en) | Front and back vehicle license plate recognition method and device based on video detection | |
| JP6859117B2 (en) | Information processing equipment, information processing methods, programs, and information processing systems | |
| CN103646550A (en) | Intelligent vehicle license plate recognition system | |
| KR100948382B1 (en) | Security service method and system | |
| CN109035446B (en) | Automatic charging system for parking lot | |
| KR101660254B1 (en) | recognizing system of vehicle number for parking crossing gate | |
| KR102181355B1 (en) | Vehicle search system based artificial intelligence | |
| CN103914980A (en) | Photographing device and image acquisition method | |
| KR20210064492A (en) | License Plate Recognition Method and Apparatus for roads | |
| CN108198433B (en) | Parking identification method and device and electronic equipment | |
| CN111241918B (en) | Vehicle tracking prevention method and system based on face recognition | |
| CN113920749A (en) | Vehicle following identification method and system for parking lot and related device | |
| CN100433040C (en) | Method and device for identifying vehicle image | |
| CN106981104B (en) | Charging monitoring method, device, server and system | |
| CN117456481A (en) | Anti-fake license plate recognition method, system and terminal | |
| CN111950499A (en) | Method for detecting vehicle-mounted personnel statistical information | |
| CN116110127A (en) | Multi-linkage gas station cashing behavior recognition system | |
| CN203192069U (en) | Snapshot system of parking lot | |
| KR102521590B1 (en) | Entrance and exit vehicle detecting apparatus and the method thereof | |
| KR20040071479A (en) | A license plate recognition system and the cars administration method thereof | |
| KR100869139B1 (en) | System for recognizing regisration number plate of vechicle using image input signal through mobile phone and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |