CN116883985A - Vehicle identification method and system - Google Patents
Vehicle identification method and system Download PDFInfo
- Publication number
- CN116883985A CN116883985A CN202310928141.9A CN202310928141A CN116883985A CN 116883985 A CN116883985 A CN 116883985A CN 202310928141 A CN202310928141 A CN 202310928141A CN 116883985 A CN116883985 A CN 116883985A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- recognition
- identification
- video
- management
- 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 65
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims description 26
- 238000010276 construction Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 8
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 14
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000012015 optical character recognition Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/36—Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
-
- 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
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Nonlinear Science (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a vehicle identification method and system, and relates to the technical field of image identification. The method comprises the following steps: constructing a vehicle management architecture; constructing a vehicle identification model; collecting and preprocessing video of vehicles entering and exiting; extracting and performing character recognition on a vehicle image containing license plates in the video of the vehicle entering and exiting so as to obtain and determine an initial vehicle information recognition result according to a plurality of license plate recognition results; determining an identification scheme by adopting a vehicle identification model according to an initial vehicle information identification result, and identifying each frame of vehicle image in the in-out vehicle video according to the identification scheme so as to obtain a vehicle identification result; compressing the video of the vehicle to obtain compressed data, and importing the compressed data and the vehicle identification result into a vehicle management framework for storage management. According to the method, a targeted vehicle management architecture and a recognition model are built by combining the characteristics of the vehicles in the community, multiple comprehensive and accurate vehicle recognition is performed, and the vehicle recognition effect and the vehicle management efficiency are improved.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to a vehicle recognition method and system.
Background
The current district property security management is gradually perfected, wherein the vehicle management is particularly important, vehicles entering the district need to be monitored and recorded, the conditions of the vehicles are mastered in real time, and the property safety of owners is ensured. At present, the supervision, judgment and recording are mainly carried out manually, the vehicle access condition of the district is supervised, a large amount of manpower and material resources are consumed, the management effect is low, and the management is inconvenient. Although intelligent recognition technology is applied to recognition management of vehicles at present, the existing vehicle recognition technology is only used for carrying out simple and single license plate information recognition based on visual images, and the recognition precision is not high; and the effective vehicle management can be realized only by matching a plurality of devices, and the cost is high.
Disclosure of Invention
In order to overcome the problems or at least partially solve the problems, the application provides a vehicle identification method and a system, which are used for constructing a targeted vehicle identification framework by combining the characteristics of a district vehicle, carrying out multiple comprehensive and accurate vehicle identification and improving the vehicle identification effect and the vehicle management efficiency.
In order to solve the technical problems, the application adopts the following technical scheme:
in a first aspect, the present application provides a vehicle identification method, comprising the steps of:
collecting and constructing a vehicle management framework according to the basic information of the district vehicles;
collecting vehicle characteristic data, constructing a vehicle characteristic database and constructing a vehicle identification model;
when a vehicle enters and exits the cell, collecting and preprocessing a video of the vehicle entering and exiting;
extracting and performing text recognition on each frame of vehicle image in the in-out vehicle video to obtain and determine an initial vehicle information recognition result according to a plurality of vehicle recognition results;
determining an identification scheme by adopting a vehicle identification model according to an initial vehicle information identification result, and identifying a vehicle image in a vehicle entering and exiting video according to the identification scheme so as to obtain a vehicle identification result;
compressing the video of the vehicle to obtain compressed data, and importing the compressed data and the vehicle identification result into a vehicle management framework for storage management.
The method builds a targeted vehicle management architecture and a vehicle identification model aiming at the basic conditions of the district vehicles and the characteristics of different vehicles so as to carry out accurate and efficient vehicle identification and vehicle management subsequently, thereby greatly improving the vehicle identification precision and management efficiency. When a vehicle enters and exits a cell, acquiring a video of the vehicle entering and exiting through a video acquisition device, preprocessing acquired video data to obtain a clearer and better video, and then carrying out initial character recognition on each frame of vehicle image in the video to obtain a preliminary vehicle information recognition result, and according to the preliminary vehicle information recognition result; and then, combining the vehicle recognition model to determine a targeted recognition scheme, and carrying out further more accurate vehicle recognition so as to obtain more accurate and comprehensive vehicle recognition results. In order to improve the vehicle management efficiency and effect, the vehicle identification result is imported into a vehicle management framework for storage management so as to be convenient for subsequent cell management personnel to call and check; in order to save the storage space, the in-out vehicle data is compressed and then stored in the vehicle management framework for storage management.
Based on the first aspect, the method for constructing the vehicle management architecture according to the basic information of the district vehicle further comprises the following steps:
extracting and setting management nodes according to the number of vehicles in the basic information of the vehicles in the district;
extracting and setting feature class sub-nodes according to the vehicle features in the basic information of the district vehicles;
and constructing a vehicle management architecture based on the management node and the feature class child nodes.
Based on the first aspect, the method for constructing the vehicle identification model further comprises the following steps:
classifying data in a vehicle characteristic database to determine a plurality of vehicle characteristic categories;
constructing an initial vehicle identification frame according to a plurality of vehicle feature categories;
a plurality of recognition schemes are set according to the plurality of vehicle feature categories, and each recognition scheme is associated with an initial vehicle recognition frame to construct a vehicle recognition model.
Based on the first aspect, the method for determining the recognition scheme according to the initial vehicle information recognition result by using the vehicle recognition model further comprises the following steps:
and importing an initial vehicle information recognition result into a vehicle recognition model, extracting and matching a corresponding recognition scheme according to the vehicle characteristic data, wherein the recognition scheme comprises a recognition range, a recognition object and a recognition algorithm.
Based on the first aspect, the method for identifying the vehicle image in the video of the vehicle according to the identification scheme to obtain the vehicle identification result further comprises the following steps:
extracting a corresponding target vehicle image in the vehicle video according to the identification range in the identification scheme;
identifying the corresponding target vehicle image according to the identification object and the identification algorithm in the identification scheme to obtain a corresponding identification result;
and clustering the recognition results to determine a final vehicle recognition result, wherein the vehicle recognition result comprises license plate information, vehicle identification and vehicle body condition information.
Based on the first aspect, the method for recognizing characters of each frame of vehicle image in the in-out vehicle video further comprises the following steps:
detecting each frame of vehicle image in the in-out vehicle video by utilizing a multi-edge detection mutual calibration method so as to obtain and screen according to a plurality of detection results to obtain a high-quality vehicle image;
and respectively identifying the high-quality vehicle images by utilizing a plurality of OCR identification models to obtain and determine a final initial vehicle information identification result according to the plurality of identification results.
Based on the first aspect, the method for preprocessing the video of the vehicle entering and exiting further comprises the following steps:
filtering each frame of image in the video of the vehicle by using any one of a plurality of filtering methods of median filtering, mean filtering and Gaussian filtering;
and carrying out detail optimization on the filtered image to obtain a better image.
In a second aspect, the present application provides a vehicle identification system, including a management architecture construction module, an identification model construction module, a video acquisition module, an initial identification module, a target identification module, and a vehicle information management module, wherein:
the management architecture construction module is used for acquiring and constructing a vehicle management architecture according to the basic information of the district vehicles;
the recognition model construction module is used for collecting vehicle characteristic data, constructing a vehicle characteristic database and constructing a vehicle recognition model;
the video acquisition module is used for acquiring and preprocessing the video of the vehicle entering and exiting when the vehicle enters and exits the cell;
the initial recognition module is used for extracting and carrying out character recognition on each frame of vehicle image in the vehicle video so as to obtain and determine initial vehicle information recognition results according to a plurality of vehicle recognition results;
the target recognition module is used for determining a recognition scheme according to an initial vehicle information recognition result by adopting a vehicle recognition model, and recognizing a vehicle image in a vehicle in-out video according to the recognition scheme so as to obtain a vehicle recognition result;
and the vehicle information management module is used for compressing the video of the vehicle entering and exiting to obtain compressed data, and importing the compressed data and the vehicle identification result into a vehicle management framework for storage management.
According to the system, through the cooperation of a plurality of modules such as the management architecture construction module, the identification model construction module, the video acquisition module, the initial identification module, the target identification module, the vehicle information management module and the like, a targeted vehicle management architecture and a vehicle identification model are constructed aiming at the basic conditions of the vehicles in the district and the characteristics of different vehicles, so that accurate and efficient vehicle identification and vehicle management can be carried out later, and the vehicle identification precision and the management efficiency are greatly improved. When a vehicle enters and exits a cell, acquiring a video of the vehicle entering and exiting through a video acquisition device, preprocessing acquired video data to obtain a clearer and better video, and then carrying out initial character recognition on each frame of vehicle image in the video to obtain a preliminary vehicle information recognition result, and according to the preliminary vehicle information recognition result; and then, combining the vehicle recognition model to determine a targeted recognition scheme, and carrying out further more accurate vehicle recognition so as to obtain more accurate and comprehensive vehicle recognition results. In order to improve the vehicle management efficiency and effect, the vehicle identification result is imported into a vehicle management framework for storage management so as to be convenient for subsequent cell management personnel to call and check; in order to save the storage space, the in-out vehicle data is compressed and then stored in the vehicle management framework for storage management.
In a third aspect, the present application provides an electronic device comprising a memory for storing one or more programs; a processor; the method of any of the first aspects described above is implemented when one or more programs are executed by a processor.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as in any of the first aspects described above.
The application has at least the following advantages or beneficial effects:
1. aiming at the basic conditions of the vehicles in the district and the characteristics of different vehicles, a targeted vehicle management architecture and a vehicle identification model are constructed so as to carry out accurate and efficient vehicle identification and vehicle management subsequently, and the vehicle identification precision and management efficiency are greatly improved; determining data processing flow according to the number of the vehicles in the cell, setting reasonable management nodes, setting a plurality of characteristic class sub-nodes according to the characteristics of the vehicles, classifying and managing, constructing a vehicle management framework by combining the management nodes and the characteristic class sub-nodes, and carrying out targeted management on the vehicles in the cell, thereby greatly improving the management efficiency, and simultaneously being convenient for subsequent management staff to visually and clearly check;
2. after compressing the in-out vehicle data, storing the compressed in-out vehicle data into a vehicle management framework for storage management, so that the storage space is greatly saved;
3. setting corresponding recognition schemes by combining different vehicle characteristics, and constructing a targeted vehicle recognition model so as to ensure the subsequent recognition efficiency and accuracy;
4. determining a targeted recognition scheme by combining the vehicle recognition model, and further carrying out more accurate vehicle recognition to obtain more accurate and comprehensive vehicle recognition results;
5. preprocessing the collected in-out vehicle videos, and respectively optimizing the images to obtain higher-quality videos, so that the accuracy and the high efficiency of subsequent recognition are improved, and invalid recognition is avoided;
6. detecting the vehicle image by utilizing a multi-edge detection mutual calibration method, and further screening out part of vehicle images with low quality and unclear images so as to obtain part of clearer high-quality vehicle images;
7. compressing the video of the in-out vehicles, importing corresponding compressed data and vehicle identification results into corresponding sub-nodes in the vehicle management framework according to the vehicle identification results for classified storage management, further improving the management effect on the vehicles in the community, and saving the storage space.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related 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 vehicle identification method according to an embodiment of the application;
FIG. 2 is a flow chart of a vehicle management architecture constructed in a vehicle identification method according to an embodiment of the present application;
FIG. 3 is a flowchart of a vehicle recognition model constructed in a vehicle recognition method according to an embodiment of the present application;
FIG. 4 is a schematic block diagram of a vehicle identification system according to an embodiment of the present application;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present application.
Reference numerals illustrate: 100. a management architecture construction module; 200. the model construction module is identified; 300. a video acquisition module; 400. an initial identification module; 500. a target recognition module; 600. a vehicle information management module; 101. a memory; 102. a processor; 103. a communication interface.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the description of the embodiments of the present application, "plurality" means at least 2.
Examples:
as shown in fig. 1 to 3, in a first aspect, an embodiment of the present application provides a vehicle identification method, including the following steps:
s1, acquiring and constructing a vehicle management framework according to basic information of a district vehicle; the cell vehicle basis information includes the number of vehicles, the vehicle attribution, the vehicle type characteristics, etc.
Further, as shown in fig. 2, includes:
s11, extracting and setting management nodes according to the number of vehicles in the basic information of the district vehicles;
s12, extracting and setting feature class sub-nodes according to the vehicle features in the cell vehicle basic information;
s13, constructing a vehicle management framework based on the management node and the feature class sub-node.
In some embodiments of the present application, in order to further improve the vehicle management efficiency, the data processing flow is determined for the number of vehicles in the cell, a reasonable management node is set, then a plurality of feature class sub-nodes are set according to the vehicle features, the classification is performed, a vehicle management architecture is constructed by combining the management node and the feature class sub-nodes, the targeted management of the vehicles in the cell is performed subsequently, the management efficiency is greatly improved, and meanwhile, the present application is convenient for subsequent management personnel to visually and clearly check. The vehicle management architecture comprises a plurality of management nodes, wherein a plurality of characteristic class sub-nodes are associated under each management node, and storage management of related class vehicle information is carried out subsequently.
S2, collecting vehicle characteristic data, constructing a vehicle characteristic database and constructing a vehicle identification model; the above-described vehicle characteristic data includes a vehicle type, a vehicle identification, a vehicle body shape structure, and the like.
Further, as shown in fig. 3, includes:
s21, classifying data in a vehicle feature database to determine a plurality of vehicle feature categories;
s22, constructing an initial vehicle identification frame according to a plurality of vehicle feature categories;
s23, setting a plurality of recognition schemes according to a plurality of vehicle feature categories, and associating each recognition scheme with an initial vehicle recognition frame to construct a vehicle recognition model.
In some embodiments of the present application, in order to ensure vehicle recognition efficiency, corresponding recognition schemes are set in combination with different vehicle features, a targeted vehicle recognition model is constructed, and different vehicle information recognition is performed according to different vehicle features, so as to ensure accuracy and high efficiency of vehicle recognition.
S3, when the vehicle enters and exits the cell, acquiring and preprocessing a video of the vehicle entering and exiting;
further, the method comprises the steps of: filtering each frame of image in the video of the vehicle by using any one of a plurality of filtering methods of median filtering, mean filtering and Gaussian filtering; and carrying out detail optimization on the filtered image to obtain a better image.
In some embodiments of the present application, in order to improve the accuracy and high efficiency of the subsequent recognition, avoid invalid recognition, the collected video of the in-out vehicle is preprocessed, and the image is optimized to obtain a better quality video, so as to provide more effective video data for the subsequent.
The filtering noise filtering for each frame of image in the video of the vehicle comprises the following specific steps: filtering the image by any one of a plurality of filtering methods such as median filtering, mean filtering, gaussian filtering and the like; and carrying out detail optimization on the filtered image to obtain a clearer image. The filtering results based on various filtering methods can be combined, so that a filtering image with better filtering effect is obtained.
S4, extracting and carrying out character recognition on each frame of vehicle image in the in-out vehicle video so as to obtain and determine an initial vehicle information recognition result according to a plurality of vehicle recognition results;
further, the method comprises the steps of: detecting each frame of vehicle image in the in-out vehicle video by utilizing a multi-edge detection mutual calibration method so as to obtain and screen according to a plurality of detection results to obtain a high-quality vehicle image; and respectively identifying the high-quality vehicle images by utilizing a plurality of OCR identification models to obtain and determine a final initial vehicle information identification result according to the plurality of identification results.
In some embodiments of the present application, in order to further ensure the recognition effect and improve the recognition efficiency, firstly, a multi-edge detection mutual verification method is used to detect the vehicle image, and then a part of the vehicle image with low quality and unclear image is screened out, so as to obtain a part of the vehicle image with better quality with clearer definition; and then respectively identifying each high-quality vehicle image by utilizing a plurality of different OCR (optical character recognition) models to obtain a plurality of vehicle information identification results corresponding to each image, and obtaining a final initial vehicle information identification result according to all the vehicle information identification results, wherein the initial vehicle information identification result comprises vehicle license plate information, vehicle identification characteristics and the like.
The detecting the vehicle image by using the multi-edge detection mutual checking method specifically comprises the following steps: detecting the edges of the vehicle image by using a Canny operator to obtain a detection result; detecting the edges of the vehicle image by using Laplacian operator to obtain a detection result; detecting the edges of the vehicle image by utilizing a Sobel operator to obtain a detection result; checking the three detection results mutually, and if the checking results show that the differences between every two detection results are lower than a preset difference threshold value, determining that the vehicle image is a high-quality vehicle image; otherwise, the vehicle image is determined to be low in quality, and the frame of vehicle image is removed.
S5, determining an identification scheme according to an initial vehicle information identification result by using a vehicle identification model, and identifying a vehicle image in a vehicle entering and exiting video according to the identification scheme so as to obtain a vehicle identification result;
further, the method comprises the steps of: and importing an initial vehicle information recognition result into a vehicle recognition model, extracting and matching a corresponding recognition scheme according to the vehicle characteristic data, wherein the recognition scheme comprises a recognition range, a recognition object and a recognition algorithm.
Further, extracting corresponding target vehicle images in the vehicle video according to the identification range in the identification scheme; identifying the corresponding target vehicle image according to the identification object and the identification algorithm in the identification scheme to obtain a corresponding identification result; and clustering the recognition results to determine a final vehicle recognition result, wherein the vehicle recognition result comprises license plate information, vehicle identification and vehicle body condition information.
In some embodiments of the present application, in order to further improve the vehicle recognition effect, different recognition schemes are constructed for different vehicle features, and corresponding recognition schemes are called by combining the vehicle recognition model with the vehicle features in the initial vehicle information recognition result, so as to perform license plate information, vehicle identification or vehicle body condition information recognition in a targeted manner; one or more kinds of information identification can be respectively carried out by combining different vehicles, so that the identification efficiency is improved, and the identification requirement is better met.
S6, compressing the video of the vehicle entering and exiting to obtain compressed data, and importing the compressed data and the vehicle identification result into a vehicle management framework for storage management.
In some embodiments of the present application, in order to further improve the management effect on the vehicles in the cell, save the storage space at the same time, compress the video of the vehicles entering and exiting, and import the corresponding compressed data and the vehicle identification result into the corresponding child nodes in the vehicle management architecture according to the vehicle identification result for classified storage management.
The method builds a targeted vehicle management architecture and a vehicle identification model aiming at the basic conditions of the district vehicles and the characteristics of different vehicles so as to carry out accurate and efficient vehicle identification and vehicle management subsequently, thereby greatly improving the vehicle identification precision and management efficiency. When a vehicle enters and exits a cell, acquiring a video of the vehicle entering and exiting through a video acquisition device, preprocessing acquired video data to obtain a clearer and better video, and then carrying out initial character recognition on each frame of vehicle image in the video to obtain a preliminary vehicle information recognition result, and according to the preliminary vehicle information recognition result; and then, combining the vehicle recognition model to determine a targeted recognition scheme, and carrying out further more accurate vehicle recognition so as to obtain more accurate and comprehensive vehicle recognition results. In order to improve the vehicle management efficiency and effect, the vehicle identification result is imported into a vehicle management framework for storage management so as to be convenient for subsequent cell management personnel to call and check; in order to save the storage space, the in-out vehicle data is compressed and then stored in the vehicle management framework for storage management.
In some embodiments of the present application, in order to further improve the vehicle recognition effect, the voice features of the vehicle may be combined to perform matching analysis, and based on a preset vehicle basic audio tone reference database, the audio in the collected vehicle video is matched and compared by combining the tone features of different vehicles, so as to recognize the relevant information corresponding to the vehicle entering and exiting. In order to better improve the audio comparison effect, denoising and optimizing the voice signals in the video of the vehicle, denoising the voice signals by using a least square method self-adaptive filter to obtain initial denoising signals, performing spatial voice signal optimization on the initial denoising signals by using Fourier transformation, performing inverse transformation to obtain final voice denoising signals, and performing accurate voice matching.
As shown in fig. 4, in a second aspect, an embodiment of the present application provides a vehicle identification system, including a management architecture construction module 100, an identification model construction module 200, a video acquisition module 300, an initial identification module 400, a target identification module 500, and a vehicle information management module 600, wherein:
the management architecture construction module 100 is configured to collect and construct a vehicle management architecture according to the basic information of the vehicles in the cell;
the recognition model construction module 200 is used for collecting vehicle characteristic data, constructing a vehicle characteristic database and constructing a vehicle recognition model;
the video acquisition module 300 is used for acquiring and preprocessing the video of the vehicle entering and exiting the cell when the vehicle enters and exiting the cell;
the initial recognition module 400 is configured to extract and perform text recognition on each frame of vehicle image in the video of the vehicle to obtain and determine an initial vehicle information recognition result according to a plurality of vehicle recognition results;
the target recognition module 500 is configured to determine a recognition scheme according to an initial vehicle information recognition result by using a vehicle recognition model, and recognize a vehicle image in a video of an incoming and outgoing vehicle according to the recognition scheme, so as to obtain a vehicle recognition result;
the vehicle information management module 600 is configured to compress the video of the vehicle entering and exiting to obtain compressed data, and import the compressed data and the vehicle identification result to the vehicle management architecture for storage management.
The system constructs a targeted vehicle management architecture and a vehicle identification model according to the basic conditions of the district vehicles and the characteristics of different vehicles through the cooperation of a plurality of modules such as the management architecture construction module 100, the identification model construction module 200, the video acquisition module 300, the initial identification module 400, the target identification module 500, the vehicle information management module 600 and the like, so that accurate and efficient vehicle identification and vehicle management can be carried out later, and the vehicle identification precision and the management efficiency are greatly improved. When a vehicle enters and exits a cell, acquiring a video of the vehicle entering and exiting through a video acquisition device, preprocessing acquired video data to obtain a clearer and better video, and then carrying out initial character recognition on each frame of vehicle image in the video to obtain a preliminary vehicle information recognition result, and according to the preliminary vehicle information recognition result; and then, combining the vehicle recognition model to determine a targeted recognition scheme, and carrying out further more accurate vehicle recognition so as to obtain more accurate and comprehensive vehicle recognition results. In order to improve the vehicle management efficiency and effect, the vehicle identification result is imported into a vehicle management framework for storage management so as to be convenient for subsequent cell management personnel to call and check; in order to save the storage space, the in-out vehicle data is compressed and then stored in the vehicle management framework for storage management.
As shown in fig. 5, in a third aspect, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs; a processor 102. The method of any of the first aspects described above is implemented when one or more programs are executed by the processor 102.
And a communication interface 103, where the memory 101, the processor 102 and the communication interface 103 are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules that are stored within the memory 101 for execution by the processor 102 to perform various functional applications and data processing. The communication interface 103 may be used for communication of signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read Only Memory (ROM), a programmable Read Only Memory (Programmable Read-Only Memory, PROM), an erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor 102 may be an integrated circuit chip with signal processing capabilities. The processor 102 may be a general purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed method and system may be implemented in other manners. The above-described method and system embodiments are merely illustrative, for example, flow charts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by the processor 102, implements a method as in any of the first aspects described above. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above is only a preferred embodiment of the present application, and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. A vehicle identification method characterized by comprising the steps of:
collecting and constructing a vehicle management framework according to the basic information of the district vehicles;
collecting vehicle characteristic data, constructing a vehicle characteristic database and constructing a vehicle identification model;
when a vehicle enters and exits the cell, collecting and preprocessing a video of the vehicle entering and exiting;
extracting and performing text recognition on each frame of vehicle image in the in-out vehicle video to obtain and determine an initial vehicle information recognition result according to a plurality of vehicle recognition results;
determining an identification scheme by adopting a vehicle identification model according to an initial vehicle information identification result, and identifying a vehicle image in a vehicle entering and exiting video according to the identification scheme so as to obtain a vehicle identification result;
compressing the video of the vehicle to obtain compressed data, and importing the compressed data and the vehicle identification result into a vehicle management framework for storage management.
2. The vehicle identification method according to claim 1, wherein the method of constructing a vehicle management architecture from cell vehicle basic information comprises the steps of:
extracting and setting management nodes according to the number of vehicles in the basic information of the vehicles in the district;
extracting and setting feature class sub-nodes according to the vehicle features in the basic information of the district vehicles;
and constructing a vehicle management architecture based on the management node and the feature class child nodes.
3. The vehicle identification method according to claim 1, characterized in that the method of constructing a vehicle identification model comprises the steps of:
classifying data in a vehicle characteristic database to determine a plurality of vehicle characteristic categories;
constructing an initial vehicle identification frame according to a plurality of vehicle feature categories;
a plurality of recognition schemes are set according to the plurality of vehicle feature categories, and each recognition scheme is associated with an initial vehicle recognition frame to construct a vehicle recognition model.
4. A vehicle identification method according to claim 3, wherein said method for determining an identification scheme based on an initial vehicle information identification result using a vehicle identification model comprises the steps of:
and importing an initial vehicle information recognition result into a vehicle recognition model, extracting and matching a corresponding recognition scheme according to the vehicle characteristic data, wherein the recognition scheme comprises a recognition range, a recognition object and a recognition algorithm.
5. The method for recognizing a vehicle according to claim 4, wherein the method for recognizing the image of the vehicle in the video of the vehicle according to the recognition scheme to obtain the result of the vehicle recognition comprises the steps of:
extracting a corresponding target vehicle image in the vehicle video according to the identification range in the identification scheme;
identifying the corresponding target vehicle image according to the identification object and the identification algorithm in the identification scheme to obtain a corresponding identification result;
and clustering the recognition results to determine a final vehicle recognition result, wherein the vehicle recognition result comprises license plate information, vehicle identification and vehicle body condition information.
6. The method for recognizing a vehicle according to claim 1, wherein the method for recognizing characters for each frame of the vehicle image in the video of the coming in and going out vehicle comprises the steps of:
detecting each frame of vehicle image in the in-out vehicle video by utilizing a multi-edge detection mutual calibration method so as to obtain and screen according to a plurality of detection results to obtain a high-quality vehicle image;
and respectively identifying the high-quality vehicle images by utilizing a plurality of OCR identification models to obtain and determine a final initial vehicle information identification result according to the plurality of identification results.
7. A vehicle identification method according to claim 1, wherein the method of preprocessing the incoming and outgoing vehicle video comprises the steps of:
filtering each frame of image in the video of the vehicle by using any one of a plurality of filtering methods of median filtering, mean filtering and Gaussian filtering;
and carrying out detail optimization on the filtered image to obtain a better image.
8. The vehicle identification system is characterized by comprising a management architecture construction module, an identification model construction module, a video acquisition module, an initial identification module, a target identification module and a vehicle information management module, wherein:
the management architecture construction module is used for acquiring and constructing a vehicle management architecture according to the basic information of the district vehicles;
the recognition model construction module is used for collecting vehicle characteristic data, constructing a vehicle characteristic database and constructing a vehicle recognition model;
the video acquisition module is used for acquiring and preprocessing the video of the vehicle entering and exiting when the vehicle enters and exits the cell;
the initial recognition module is used for extracting and carrying out character recognition on each frame of vehicle image in the vehicle video so as to obtain and determine initial vehicle information recognition results according to a plurality of vehicle recognition results;
the target recognition module is used for determining a recognition scheme according to an initial vehicle information recognition result by adopting a vehicle recognition model, and recognizing a vehicle image in a vehicle in-out video according to the recognition scheme so as to obtain a vehicle recognition result;
and the vehicle information management module is used for compressing the video of the vehicle entering and exiting to obtain compressed data, and importing the compressed data and the vehicle identification result into a vehicle management framework for storage management.
9. An electronic device, comprising:
a memory for storing one or more programs;
a processor;
the method of any of claims 1-7 is implemented when the one or more programs are executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310928141.9A CN116883985A (en) | 2023-07-26 | 2023-07-26 | Vehicle identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310928141.9A CN116883985A (en) | 2023-07-26 | 2023-07-26 | Vehicle identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116883985A true CN116883985A (en) | 2023-10-13 |
Family
ID=88264278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310928141.9A Pending CN116883985A (en) | 2023-07-26 | 2023-07-26 | Vehicle identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116883985A (en) |
-
2023
- 2023-07-26 CN CN202310928141.9A patent/CN116883985A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428091B (en) | Risk identification method based on data analysis and related equipment | |
| JP2022526382A (en) | Behavioral analytics methods, devices, electronic devices, storage media and computer programs | |
| CN104239881A (en) | Method and system for automatically finding and registering target in surveillance video | |
| CN105405054A (en) | Insurance claim antifraud implementation method based on claim photo deep learning and server | |
| CN112200081A (en) | Abnormal behavior identification method and device, electronic equipment and storage medium | |
| CN111859451B (en) | Multi-source multi-mode data processing system and method for applying same | |
| CN104750800A (en) | Motor vehicle clustering method based on travel time characteristic | |
| CN104199903A (en) | Vehicle data query system and method based on path correlation | |
| WO2022213336A1 (en) | Vehicle driving environment abnormality monitoring method and apparatus, electronic device, and storage medium | |
| CN112580531B (en) | Identification detection method and system for true and false license plates | |
| CN113902993A (en) | Environmental state analysis method and system based on environmental monitoring | |
| CN114333343A (en) | Non-motor vehicle violation snapshot evidence obtaining device, method and system | |
| CN114139016A (en) | Data processing method and system for intelligent cell | |
| CN116705250A (en) | Low-consumption optimization and intelligent storage method and system for medical image big data | |
| CN116883985A (en) | Vehicle identification method and system | |
| CN112216374A (en) | Medical service supervision method, device and equipment | |
| CN116939164A (en) | Security monitoring method and system | |
| CN116993517A (en) | Vehicle insurance claim fraud identification method, device, equipment and storage medium | |
| CN116778460A (en) | Fatigue driving identification method based on image identification | |
| CN116448234A (en) | Power transformer running state voiceprint monitoring method and system | |
| CN115880632A (en) | Timeout stay detection method, monitoring device, computer-readable storage medium, and chip | |
| CN109308673A (en) | A kind of source of houses monitoring and managing method and device | |
| KR102435435B1 (en) | System for searching numbers of vehicle and pedestrian based on artificial intelligence | |
| CN111369394B (en) | Scenic spot passenger flow volume statistical evaluation system and method based on big data | |
| CN114241195A (en) | Target identification method and device, electronic equipment and storage medium |
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 |