CN113486885A - License plate recognition method and device, electronic equipment and storage medium - Google Patents
License plate recognition method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113486885A CN113486885A CN202110671452.2A CN202110671452A CN113486885A CN 113486885 A CN113486885 A CN 113486885A CN 202110671452 A CN202110671452 A CN 202110671452A CN 113486885 A CN113486885 A CN 113486885A
- Authority
- CN
- China
- Prior art keywords
- license plate
- target vehicle
- recognition result
- character
- vehicle
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 26
- 238000001514 detection method Methods 0.000 claims description 20
- 238000013145 classification model Methods 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 6
- 230000029087 digestion Effects 0.000 description 4
- 230000006403 short-term memory Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 239000002356 single layer Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Character Discrimination (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application discloses a license plate identification method, a license plate identification device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a license plate region image of a target vehicle passing through a specific scene, and performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle; determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle; inputting the license plate area image into a character recognition model to obtain a character recognition result of the target vehicle; and determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle. According to the license plate character combination rule and the characters, the license plate of the target vehicle is recognized, the accuracy of license plate recognition is improved, and therefore the vehicle management process is perfected.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a license plate recognition method and device, electronic equipment and a storage medium.
Background
Large vehicles are the key points of urban construction, and vehicles at various construction sites are scientifically managed, so that the traffic and transportation cost is reduced. With the acceleration of urban construction and the ever-increasing number of miniaturized sites, the challenge is presented to unified vehicle management.
In order to deal with the challenges, the license plate recognition system is produced, and is widely applied to specific scenes due to the advantages of reducing vehicle management and operation cost and the like. However, the accuracy of license plate recognition is affected by various factors, such as the shooting angle of a camera, the driving speed, the external ambient light, shading, the stained license plate, the similarity of characters of the license plate, and the like. At present, the accuracy of license plate recognition equipment based on video image license plate recognition is not high, and the recognition rate of a license plate recognition system still has more space for improvement.
Disclosure of Invention
Because the existing methods have the problems, embodiments of the present application provide a license plate recognition method, a license plate recognition device, an electronic device, and a storage medium.
Specifically, the embodiment of the present application provides the following technical solutions:
in a first aspect, an embodiment of the present application provides a license plate recognition method, including:
acquiring a license plate region image of a target vehicle passing through a specific scene, and performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle;
determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle;
inputting the license plate region image into a character recognition model to obtain a character recognition result of the target vehicle;
and determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
Optionally, the obtaining of the license plate region image of the target vehicle passing through the specific scene includes:
acquiring a vehicle image of a target vehicle passing through a specific scene;
inputting the vehicle image into a target detection model to obtain a license plate area image when the target vehicle passes through a specific scene; the target detection model is obtained by training a deep learning target detection neural network model based on random vehicle images of a specific scene and license plate region images corresponding to the random vehicle images.
Optionally, performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle, including:
inputting the license plate region image into a classification model to obtain the license plate type of the target vehicle; the classification model is obtained by training a graph convolution neural network based on random license plate region images and license plate types corresponding to the random license plate region images.
Optionally, the character recognition model is obtained by training a long-short term memory network LSTM based on a first training sample set and a second training sample set; the first training sample set includes character recognition results of a target vehicle over a specified period of time in the past; the second training sample set comprises character recognition results which meet preset approximate standards with the target vehicle within a specified time period in the future.
Optionally, determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle, including:
determining the position of Chinese characters and the position of non-Chinese characters in the license plate of the target vehicle according to the license plate character combination rule of the target vehicle;
and matching and sequencing the character recognition result of the target vehicle with the position of the Chinese character and the position of the non-Chinese character in the license plate of the target vehicle, and determining the license plate recognition result of the target vehicle.
Optionally, when the character recognition result includes unrecognized characters, determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle, including:
acquiring a character recognition result which is output by the character recognition model and accords with a preset approximate standard with a target vehicle in a past appointed time period;
and replacing the unrecognized characters with characters corresponding to the character recognition result of the target vehicle which accords with the preset approximate standard according to the character recognition result of the target vehicle which accords with the preset approximate standard, so that the license plate recognition result of the target vehicle is determined according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
In a second aspect, an embodiment of the present application provides a license plate recognition device, including:
the system comprises a first processing module, a second processing module and a third processing module, wherein the first processing module is used for acquiring a license plate region image when a target vehicle passes through a specific scene, and performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle;
the second processing module is used for determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle;
the third processing module is used for inputting the license plate area image into a character recognition model to obtain a character recognition result of the target vehicle;
and the fourth processing module is used for determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
Optionally, the first processing module is specifically configured to:
acquiring a vehicle image of a target vehicle passing through a specific scene;
inputting the vehicle image into a target detection model to obtain a license plate area image when the target vehicle passes through a specific scene; the target detection model is obtained by training a deep learning target detection neural network model based on random vehicle images of a specific scene and license plate region images corresponding to the random vehicle images.
In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the license plate recognition method according to the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the license plate recognition method according to the first aspect.
According to the technical scheme, the license plate region image of the target vehicle passing through the specific scene is obtained, meanwhile, the feature recognition is carried out on the license plate region image, the license plate type of the target vehicle is obtained, and further the license plate character combination rule of the target vehicle is determined according to the license plate type of the target vehicle. In addition, the license plate region image is input into the character recognition model, and a character recognition result of the target vehicle is obtained, so that the license plate recognition result of the target vehicle is determined according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle. According to the license plate character combination rule and the characters, the license plate of the target vehicle is recognized, and the accuracy of license plate recognition is improved, so that the vehicle management process is perfected, and the vehicle management operation cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart illustrating steps of a license plate recognition method according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a license plate recognition device according to an embodiment of the present disclosure;
fig. 3 is a second schematic structural diagram of a license plate recognition device according to an embodiment of the present application;
fig. 4 is a schematic diagram of a license plate recognition device provided in an embodiment of the present application, applied in a specific scene;
fig. 5 is a schematic structural diagram of a license plate recognition system according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
As shown in fig. 1, a license plate recognition method provided in an embodiment of the present application includes:
step 101: acquiring a license plate region image of a target vehicle passing through a specific scene, and performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle;
in this step, taking a scene at an exit of a construction site or a digestion site as an example, the license plate region image includes a license plate of a vehicle and images of a small number of surrounding regions. The method comprises the steps of obtaining a vehicle image through a camera arranged at an exit of a construction site or a digestion site, determining the position of a license plate area image in the vehicle image, such as the head or tail of a vehicle in the vehicle image, and inputting the image at the head or the parking space into a pre-trained target detection model to obtain an accurate license plate area image. The target detection model may be a deep learning neural network model formed by a convolutional neural network, and is not limited in particular here.
In this step, feature recognition may be performed on the acquired license plate region image according to a pre-trained classification model to obtain a license plate type, where the license plate type may include a blue plate, a single-layer yellow plate, a double-layer yellow plate, an energy-saving green plate, and the like. The classification model can adopt a graph convolution neural network formed by a convolution layer pooling layer and a full connection layer, the license plate region image is input into the classification model, various classification results can be obtained, and the license plate type can be determined.
Step 102: determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle;
in this step, a license plate character combination rule of the target vehicle may be determined according to the determined license plate type, so as to perform license plate recognition subsequently. For example, if the determined license plate type is a blue plate, the character combination rule of the corresponding blue plate vehicle can be obtained, including 1-bit kanji character and 6 non-kanji characters. For another example, if the determined license plate type is a double-layer yellow plate, the corresponding character combination rule of the double-layer yellow plate vehicle comprises an upper row and a lower row, the card-up characters comprise 1-bit Chinese characters and 1-bit non-Chinese characters, and the lower row of characters comprises 5 non-Chinese characters.
Step 103: inputting the license plate region image into a character recognition model to obtain a character recognition result of the target vehicle;
in this step, the license plate region image is input into a character recognition model obtained by training a Long Short-Term Memory network (LSTM), and a character recognition result of the target vehicle is output. Wherein the character recognition result comprises recognized characters and unrecognized characters.
Step 104: and determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
In this step, the license plate recognition result of the target vehicle can be determined according to the license plate character combination rule and the character recognition result corresponding to the target vehicle. When the character recognition results are recognized characters, the output license plate recognition result can be regarded as an accurate license plate of the target vehicle. When the character recognition result includes unrecognized characters, a character recognition result which is output by the character recognition model after the target vehicle passes through a specific scene within a past specified time period and meets a preset approximate standard with the target vehicle can be obtained. And then, the license plate recognition result of the target vehicle is reasonably predicted according to the character recognition result which accords with the preset approximate standard with the target vehicle and the ticket character combination rule of the character recognition result. For example, a license plate of a vehicle a recognized after passing through a specific scene in the past is ji A1D456, the recognition result is stored, and a character recognition result of a vehicle a passing through a specific scene again at a certain time is ji A1D 45? Then, search for the file in the database of the background storage with the wing A1D 45? The nearest character recognition result, i.e., wing A1D456, can be regarded as the license plate recognition result of the target vehicle by wing A1D 456.
According to the technical scheme, the license plate region image of the target vehicle passing through the specific scene is obtained, the feature recognition is carried out on the license plate region image to obtain the license plate type of the target vehicle, and then the license plate character combination rule of the target vehicle is determined according to the license plate type of the target vehicle. In addition, the license plate region image is input into the character recognition model, and a character recognition result of the target vehicle is obtained, so that the license plate recognition result of the target vehicle is determined according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle. According to the license plate character combination rule and the characters, the license plate of the target vehicle is recognized, and the accuracy of license plate recognition is improved, so that the vehicle management process is perfected, and the vehicle management operation cost is reduced.
Based on the content of the foregoing embodiment, in this embodiment, the acquiring a license plate region image of a target vehicle passing through a specific scene includes:
acquiring a vehicle image of a target vehicle passing through a specific scene;
inputting the vehicle image into a target detection model to obtain a license plate area image when the target vehicle passes through a specific scene; the target detection model is obtained by training a deep learning neural network model based on random vehicle images of a specific scene and license plate region images corresponding to the random vehicle images.
Based on the content of the foregoing embodiment, in this embodiment, performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle includes:
inputting the license plate region image into a classification model to obtain the license plate type of the target vehicle; the classification model is obtained by training a graph convolution neural network based on a random license plate region image and a license plate type corresponding to the random license plate region image; the graph convolution neural network is obtained through specific design and tailoring.
Based on the content of the foregoing embodiment, in this embodiment, the character recognition model is obtained by training a long-short term memory network LSTM based on a first training sample set and a second training sample set; the first training sample set includes character recognition results of a target vehicle over a specified period of time in the past; the second training sample set comprises character recognition results which meet preset approximate standards with the target vehicle within a specified time period in the future.
Based on the content of the foregoing embodiment, in this embodiment, determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle includes:
determining the position of Chinese characters and the position of non-Chinese characters in the license plate of the target vehicle according to the license plate character combination rule of the target vehicle;
and matching and sequencing the character recognition result of the target vehicle with the position of the Chinese character and the position of the non-Chinese character in the license plate of the target vehicle, and determining the license plate recognition result of the target vehicle.
Based on the content of the foregoing embodiment, in this embodiment, when the character recognition result includes an unrecognized character, determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle, including:
acquiring a character recognition result which is output by the character recognition model and accords with a preset approximate standard with a target vehicle in a past appointed time period;
and replacing the unrecognized characters with characters corresponding to the character recognition result of the target vehicle which accords with the preset approximate standard according to the character recognition result of the target vehicle which accords with the preset approximate standard, so that the license plate recognition result of the target vehicle is determined according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
In this embodiment, it should be noted that, on one hand, when the character recognition result includes unrecognized characters, the license plate recognition may be assisted by the character recognition result that is output by the character recognition model and meets the preset approximate standard with the target vehicle in the past specified time period. On the other hand, the license plate recognition of the target vehicle can be assisted by continuously tracking the license plates within a period of time and selecting the nearest license plate recognition result. Specifically, when the license plate of the vehicle passing through at present cannot be identified due to motion blur or dirt abrasion, a series of license plate identification results can be obtained through tracking a period of time before and after the identification, and finally the license plate identification result which best meets the conditions is judged through an algorithm. For example, the actual license plate of a car a is Ji A1D456, and the recognition result of a certain time is Ji A1D 45? Or the Ji A1456, through tracking for a period of time, obtains a series of recognition results, including Ji A1D456, and after judgment through an algorithm, obtains the result Ji A1D456 which best meets the conditions. Based on the same inventive concept, another embodiment of the present invention provides a license plate recognition device, as shown in fig. 2, the license plate recognition device provided in the embodiment of the present application includes:
the system comprises a first processing module 1, a second processing module and a third processing module, wherein the first processing module is used for acquiring a license plate region image when a target vehicle passes through a specific scene, and performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle;
the second processing module 2 is used for determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle;
the third processing module 3 is configured to input the license plate region image into a character recognition model, so as to obtain a character recognition result of the target vehicle;
and the fourth processing module 4 is configured to determine a license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
In this embodiment, taking a scene at an exit of a building site or a digestion site as an example, the license plate region image includes a license plate of a vehicle and images of a small number of surrounding regions. The method comprises the steps of obtaining a vehicle image through a camera arranged at an exit of a construction site or a digestion site, determining the position of a license plate area image in the vehicle image, such as the head or tail of a vehicle in the vehicle image, and inputting the image at the head or the parking space into a pre-trained target detection model to obtain an accurate license plate area image. The target detection model may be a deep learning neural network model formed by a convolutional neural network, and is not limited in particular here.
In this embodiment, feature recognition may be performed on the acquired license plate region image according to a pre-trained classification model to obtain a license plate type, where the license plate type may include a blue plate, a single-layer yellow plate, a double-layer yellow plate, an energy-saving green plate, and the like. The classification model can adopt a graph convolution neural network formed by a convolution layer pooling layer and a full connection layer, the license plate region image is input into the classification model, various classification results can be obtained, and the license plate type can be determined.
In this embodiment, a license plate character combination rule of a target vehicle may be determined according to the determined license plate type, so as to perform license plate recognition subsequently. For example, if the determined license plate type is a blue plate, the character combination rule of the corresponding blue plate vehicle can be obtained, including 1-bit kanji character and 6 non-kanji characters. For another example, if the determined license plate type is a double-layer yellow plate, the corresponding character combination rule of the double-layer yellow plate vehicle comprises an upper row and a lower row, the card-up characters comprise 1-bit Chinese characters and 1-bit non-Chinese characters, and the lower row of characters comprises 5 non-Chinese characters.
In this embodiment, the license plate region image is input to a character recognition model obtained by training a Long Short-Term Memory network LSTM (Long Short-Term Memory), and a character recognition result of the target vehicle is output. Wherein the character recognition result comprises recognized characters and unrecognized characters.
In this embodiment, the license plate recognition result of the target vehicle can be determined according to the license plate character combination rule and the character recognition result corresponding to the target vehicle. When the character recognition results are recognized characters, the output license plate recognition result can be regarded as an accurate license plate of the target vehicle. When the character recognition result includes unrecognized characters, a character recognition result which is output by the character recognition model after the target vehicle passes through a specific scene within a past specified time period and meets a preset approximate standard with the target vehicle can be obtained. And then, the license plate recognition result of the target vehicle is reasonably predicted according to the character recognition result which accords with the preset approximate standard with the target vehicle and the ticket character combination rule of the character recognition result. For example, a license plate of a vehicle a recognized after passing through a specific scene in the past is ji A1D456, the recognition result is stored, and a character recognition result of a vehicle a passing through a specific scene again at a certain time is ji A1D 45? Then, search for the file in the database of the background storage with the wing A1D 45? The nearest character recognition result, i.e., wing A1D456, can be regarded as the license plate recognition result of the target vehicle by wing A1D 456.
According to the technical scheme, the license plate region image of the target vehicle passing through the specific scene is obtained, the feature recognition is carried out on the license plate region image to obtain the license plate type of the target vehicle, and then the license plate character combination rule of the target vehicle is determined according to the license plate type of the target vehicle. In addition, the license plate region image is input into the character recognition model, and a character recognition result of the target vehicle is obtained, so that the license plate recognition result of the target vehicle is determined according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle. According to the license plate character combination rule and the characters, the license plate of the target vehicle is recognized, and the accuracy of license plate recognition is improved, so that the vehicle management process is perfected, and the vehicle management operation cost is reduced.
Based on the content of the foregoing embodiment, in this embodiment, the first processing module is specifically configured to:
acquiring a vehicle image of a target vehicle passing through a specific scene;
inputting the vehicle image into a target detection model to obtain a license plate area image when the target vehicle passes through a specific scene; the target detection model is obtained by training a deep learning neural network model based on random vehicle images of a specific scene and license plate region images corresponding to the random vehicle images.
The license plate recognition device described in this embodiment may be used to implement the above method embodiments, and the principle and technical effect are similar, which are not described herein again.
Based on the same inventive concept, another embodiment of the present application further provides a license plate recognition device and a system, and fig. 3 is a second schematic structural diagram of the license plate recognition device provided in the embodiment of the present application; fig. 4 is a schematic diagram of a license plate recognition device provided in an embodiment of the present application, applied in a specific scene; fig. 5 is a schematic structural diagram of a license plate recognition system according to an embodiment of the present disclosure; in the embodiment, the server is installed in a room with a stable environment, receives the uploaded license plate recognition result and screenshot through a network, and analyzes and provides a query. And returning any record to perform secondary verification through a terminal request. The intelligent recognition terminal is connected with the camera through wiring, and the intelligent recognition terminal and the multimedia intelligent central control screen are not limited in position and meet the requirements of actual environments. As most engineering vehicles work at night, the light supplement lamp is additionally arranged as required under the condition of lacking of lighting conditions. The camera is installed on the upright post at any side of the road at the exit, and the picture needs to contain complete vehicle head information. The protection grade required by outdoor equipment is not lower than IP66, and the wiring is uniformly wrapped by waterproof glue to prevent short circuit of the circuit. If the terminal is not indoors, a rain-proof box with a proper size needs to be equipped. The visual field of the camera is required to be contained in the license plate area as far as possible, the installation height and the distance from the inlet and the outlet are determined according to specific environments.
In this embodiment, the license plate recognition system includes software and related hardware. The intelligent identification algorithm comprises image acquisition, image identification, service logic processing, data storage query and analysis; the hardware supporting equipment comprises a camera, an intelligent identification terminal, a multimedia intelligent central control screen and a background data server. The camera is easily installed, can install in different positions according to concrete scene is nimble, then sends into intelligent recognition terminal through the video transmission line and handles and upload. The central control screen is used for displaying the current live information, inquiring and secondary checking, and can be placed in a place where the user can conveniently operate. The background data server is used for storing the captured videos or pictures and providing big data analysis or record query service. The whole working flow of software and hardware is as follows: the camera collects video streams and sends the video streams to the intelligent identification terminal to reason frame by frame, license plates and license plate numbers are identified through an AI algorithm, information is transmitted to the multimedia intelligent central control screen to be displayed and transmitted to the background server to be stored and analyzed, and meanwhile schemes of illegal vehicle warning, entering and exiting record inquiry, vehicle entering and exiting condition statistics and the like are provided. The administrator can view the recorded vehicle information on the central control screen in real time. The number of the same vehicle is continuously tracked during the identification period, so that the situation that background storage resources are wasted by repeatedly uploading the information of the same vehicle is prevented.
Based on the same inventive concept, another embodiment of the present invention provides an electronic device, which refers to the schematic structural diagram of the electronic device shown in fig. 6, and specifically includes the following contents: a processor 601, a memory 602, a communication interface 603, and a communication bus 604;
the processor 601, the memory 602 and the communication interface 603 complete mutual communication through the communication bus 604; the communication interface 603 is used for implementing information transmission between the devices;
the processor 601 is configured to call a computer program in the memory 602, and when the processor executes the computer program, the processor implements all steps of the above license plate recognition method, for example, acquiring a license plate region image when a target vehicle passes through a specific scene, and performing feature recognition on the license plate region image to obtain a license plate type of the target vehicle; determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle; inputting the license plate region image into a character recognition model to obtain a character recognition result of the target vehicle; and determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
Based on the same inventive concept, another embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements all the steps of the above license plate recognition method, for example, acquiring a license plate area image of a target vehicle passing through a specific scene, and performing feature recognition on the license plate area image to obtain a license plate type of the target vehicle; determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle; inputting the license plate region image into a character recognition model to obtain a character recognition result of the target vehicle; and determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the technical solutions mentioned above may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the license plate recognition method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A license plate recognition method is characterized by comprising the following steps:
acquiring a license plate region image of a target vehicle passing through a specific scene, and performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle;
determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle;
inputting the license plate region image into a character recognition model to obtain a character recognition result of the target vehicle;
and determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
2. The license plate recognition method of claim 1, wherein the obtaining of the license plate region image of the target vehicle passing through the specific scene comprises:
acquiring a vehicle image of a target vehicle passing through a specific scene;
inputting the vehicle image into a target detection model to obtain a license plate area image when the target vehicle passes through a specific scene; the target detection model is obtained by training a deep learning target detection neural network model based on random vehicle images of a specific scene and license plate region images corresponding to the random vehicle images.
3. The license plate recognition method of claim 1, wherein the performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle comprises:
inputting the license plate region image into a classification model to obtain the license plate type of the target vehicle; the classification model is obtained by training a graph convolution neural network based on random license plate region images and license plate types corresponding to the random license plate region images.
4. The license plate recognition method of claim 1, wherein the character recognition model is obtained by training a long-short term memory network (LSTM) based on a first training sample set and a second training sample set; the first training sample set includes character recognition results of a target vehicle over a specified period of time in the past; the second training sample set comprises character recognition results which meet preset approximate standards with the target vehicle within a specified time period in the future.
5. The license plate recognition method of claim 1, wherein determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle comprises:
determining the position of Chinese characters and the position of non-Chinese characters in the license plate of the target vehicle according to the license plate character combination rule of the target vehicle;
and matching and sequencing the character recognition result of the target vehicle with the position of the Chinese character and the position of the non-Chinese character in the license plate of the target vehicle, and determining the license plate recognition result of the target vehicle.
6. The license plate recognition method of claim 1 or 4, wherein when the character recognition result comprises unrecognized characters, determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle, comprises:
acquiring a character recognition result which is output by the character recognition model and accords with a preset approximate standard with a target vehicle in a past appointed time period;
and replacing the unrecognized characters with characters corresponding to the character recognition result of the target vehicle which accords with the preset approximate standard according to the character recognition result of the target vehicle which accords with the preset approximate standard, so that the license plate recognition result of the target vehicle is determined according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
7. A license plate recognition device, comprising:
the system comprises a first processing module, a second processing module and a third processing module, wherein the first processing module is used for acquiring a license plate region image when a target vehicle passes through a specific scene, and performing feature recognition on the license plate region image to obtain the license plate type of the target vehicle;
the second processing module is used for determining a license plate character combination rule of the target vehicle according to the license plate type of the target vehicle;
the third processing module is used for inputting the license plate area image into a character recognition model to obtain a character recognition result of the target vehicle;
and the fourth processing module is used for determining the license plate recognition result of the target vehicle according to the license plate character combination rule of the target vehicle and the character recognition result of the target vehicle.
8. The license plate recognition device of claim 7, wherein the first processing module is specifically configured to:
acquiring a vehicle image of a target vehicle passing through a specific scene;
inputting the vehicle image into a target detection model to obtain a license plate area image when the target vehicle passes through a specific scene; the target detection model is obtained by training a deep learning target detection neural network model based on random vehicle images of a specific scene and license plate region images corresponding to the random vehicle images.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the license plate recognition method according to any one of claims 1 to 6 are implemented when the program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the license plate recognition method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110671452.2A CN113486885A (en) | 2021-06-17 | 2021-06-17 | License plate recognition method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110671452.2A CN113486885A (en) | 2021-06-17 | 2021-06-17 | License plate recognition method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113486885A true CN113486885A (en) | 2021-10-08 |
Family
ID=77933870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110671452.2A Withdrawn CN113486885A (en) | 2021-06-17 | 2021-06-17 | License plate recognition method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113486885A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115701874A (en) * | 2022-11-10 | 2023-02-14 | 长沙市智慧交通发展中心 | Road operation vehicle state monitoring system and method based on target identification |
| CN116884214A (en) * | 2023-07-10 | 2023-10-13 | 珠海大横琴城市公共资源经营管理有限公司 | Monitoring and early warning method and system for municipal vehicle |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108205670A (en) * | 2016-12-16 | 2018-06-26 | 杭州海康威视数字技术股份有限公司 | A kind of licence plate recognition method and device |
| CN110490179A (en) * | 2018-05-15 | 2019-11-22 | 杭州海康威视数字技术股份有限公司 | Licence plate recognition method, device and storage medium |
| CN110781882A (en) * | 2019-09-11 | 2020-02-11 | 南京钰质智能科技有限公司 | License plate positioning and identifying method based on YOLO model |
| CN110942071A (en) * | 2019-12-09 | 2020-03-31 | 上海眼控科技股份有限公司 | License plate recognition method based on license plate classification and LSTM |
| CN111027555A (en) * | 2018-10-09 | 2020-04-17 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device and electronic equipment |
| CN111325206A (en) * | 2020-03-03 | 2020-06-23 | 山东浪潮通软信息科技有限公司 | License plate information identification and entry equipment construction method and device |
| CN111507337A (en) * | 2020-04-10 | 2020-08-07 | 河海大学 | License plate recognition method based on hybrid neural network |
| CN111582261A (en) * | 2020-04-30 | 2020-08-25 | 浙江大华技术股份有限公司 | License plate recognition method and device for non-motor vehicle |
| CN111639598A (en) * | 2020-05-29 | 2020-09-08 | 济南博观智能科技有限公司 | License plate recognition method, license plate recognition device, license plate recognition equipment and storage medium |
| CN112861840A (en) * | 2021-03-10 | 2021-05-28 | 上海交通大学 | Complex scene character recognition method and system based on multi-feature fusion convolutional network |
-
2021
- 2021-06-17 CN CN202110671452.2A patent/CN113486885A/en not_active Withdrawn
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108205670A (en) * | 2016-12-16 | 2018-06-26 | 杭州海康威视数字技术股份有限公司 | A kind of licence plate recognition method and device |
| CN110490179A (en) * | 2018-05-15 | 2019-11-22 | 杭州海康威视数字技术股份有限公司 | Licence plate recognition method, device and storage medium |
| CN111027555A (en) * | 2018-10-09 | 2020-04-17 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device and electronic equipment |
| CN110781882A (en) * | 2019-09-11 | 2020-02-11 | 南京钰质智能科技有限公司 | License plate positioning and identifying method based on YOLO model |
| CN110942071A (en) * | 2019-12-09 | 2020-03-31 | 上海眼控科技股份有限公司 | License plate recognition method based on license plate classification and LSTM |
| CN111325206A (en) * | 2020-03-03 | 2020-06-23 | 山东浪潮通软信息科技有限公司 | License plate information identification and entry equipment construction method and device |
| CN111507337A (en) * | 2020-04-10 | 2020-08-07 | 河海大学 | License plate recognition method based on hybrid neural network |
| CN111582261A (en) * | 2020-04-30 | 2020-08-25 | 浙江大华技术股份有限公司 | License plate recognition method and device for non-motor vehicle |
| CN111639598A (en) * | 2020-05-29 | 2020-09-08 | 济南博观智能科技有限公司 | License plate recognition method, license plate recognition device, license plate recognition equipment and storage medium |
| CN112861840A (en) * | 2021-03-10 | 2021-05-28 | 上海交通大学 | Complex scene character recognition method and system based on multi-feature fusion convolutional network |
Non-Patent Citations (1)
| Title |
|---|
| 陈强，等: ""基于深度学习的车牌识别系统开发研究"", 《现代计算机》, vol. 1, no. 12, pages 160 - 66 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115701874A (en) * | 2022-11-10 | 2023-02-14 | 长沙市智慧交通发展中心 | Road operation vehicle state monitoring system and method based on target identification |
| CN116884214A (en) * | 2023-07-10 | 2023-10-13 | 珠海大横琴城市公共资源经营管理有限公司 | Monitoring and early warning method and system for municipal vehicle |
| CN116884214B (en) * | 2023-07-10 | 2024-01-26 | 珠海大横琴城市公共资源经营管理有限公司 | Monitoring and early warning method and system for municipal vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN110047319B (en) | Parking lot parking space navigation method, electronic device and storage medium | |
| US11587327B2 (en) | Methods and systems for accurately recognizing vehicle license plates | |
| CN104239309A (en) | Video analysis retrieval service side, system and method | |
| CN113486885A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN111931683B (en) | Image recognition method, device and computer readable storage medium | |
| CN112183166A (en) | Method and device for determining training sample and electronic equipment | |
| CN112164227B (en) | Parking violation vehicle warning method and device, computer equipment and storage medium | |
| CN106991821A (en) | Vehicles peccancy hand-held mobile terminal data collecting system | |
| CN111311766A (en) | Roadside parking intelligent charging system and method based on license plate recognition and tracking technology | |
| CN114418895A (en) | Driving assistance method and device, vehicle-mounted device and storage medium | |
| Hakim et al. | Implementation of an image processing based smart parking system using Haar-Cascade method | |
| CN112766069A (en) | Vehicle illegal parking detection method and device based on deep learning and electronic equipment | |
| CN112434566A (en) | Passenger flow statistical method and device, electronic equipment and storage medium | |
| CN112215190A (en) | Illegal building detection method based on YOLOV4 model | |
| CN114445780A (en) | Detection method and device for bare soil covering, and training method and device for recognition model | |
| CN115063746A (en) | Vehicle warehousing management method and device, computer equipment and storage medium | |
| CN116912517B (en) | Method and device for detecting camera view field boundary | |
| CN112115737B (en) | Vehicle orientation determining method and device and vehicle-mounted terminal | |
| Song et al. | Vision-based parking space detection: A mask R-CNN approach | |
| Wang et al. | Real-time non-motor vehicle violation detection in traffic scenes | |
| CN111767904B (en) | Traffic incident detection method, device, terminal and storage medium | |
| CN113158852B (en) | Traffic gate monitoring system based on face and non-motor vehicle cooperative identification | |
| CN114693722A (en) | Vehicle driving behavior detection method, detection device and detection equipment |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211008 |
|
| WW01 | Invention patent application withdrawn after publication |