CN108805121B - License plate detection and positioning method, device, equipment and computer readable medium - Google Patents
License plate detection and positioning method, device, equipment and computer readable medium Download PDFInfo
- Publication number
- CN108805121B CN108805121B CN201710300702.5A CN201710300702A CN108805121B CN 108805121 B CN108805121 B CN 108805121B CN 201710300702 A CN201710300702 A CN 201710300702A CN 108805121 B CN108805121 B CN 108805121B
- Authority
- CN
- China
- Prior art keywords
- license plate
- vehicle
- sample image
- detection model
- image
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 58
- 238000013135 deep learning Methods 0.000 claims description 20
- 230000009466 transformation Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 230000001629 suppression Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06V20/63—Scene text, e.g. street names
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a license plate detection and positioning method, a device, equipment and a computer readable medium, wherein the method comprises the following steps: a sample image obtaining step, namely obtaining a vehicle sample image and a license plate sample image; a sample image training step, wherein the obtained vehicle sample image and the license plate sample image are trained to obtain a license plate detection model; and a license plate detection positioning step, namely acquiring a vehicle image, and inputting the vehicle image into a license plate detection model to obtain the position of the license plate. The method has the technical effects that a vehicle and license plate detection model is established based on an SSD model, a circumscribed rectangle of a license plate is marked based on vehicle information, and the accurate position of the license plate is further identified based on color and shape characteristics.
Description
Technical Field
The invention relates to the technical field of pattern recognition, in particular to a license plate detection and positioning method, a license plate detection and positioning device, license plate detection and positioning equipment and a computer readable medium.
Background
With the development of economy, the living standard of people is increasingly improved, and correspondingly, the number of motor vehicles is increased year by year. The traffic information volume and the used vehicle buying and selling quantity are increased rapidly. In order to effectively manage the information of the motor vehicle, a feasible license plate recognition system is particularly expensive. In addition, the license plate is the privacy of the user, and it is also very important to hide the user information in the picture.
However, most of the prior art depends on manual work, and the prior art is dull and inefficient, which causes manpower waste. The existing license plate system is mainly used for detecting based on a background, but for example, a blue license plate is difficult to locate for a blue vehicle or a blue background, so that the license plate locating precision is reduced.
Disclosure of Invention
The present invention provides the following technical solutions to overcome the above-mentioned drawbacks in the prior art.
A license plate detection and positioning method comprises the following steps:
a sample image obtaining step, namely obtaining a vehicle sample image and a license plate sample image;
a sample image training step, wherein the obtained vehicle sample image and the license plate sample image are trained to obtain a license plate detection model;
and a license plate detection positioning step, namely acquiring a vehicle image, and inputting the vehicle image into a license plate detection model to obtain the position of the license plate.
Further, the sample image training step specifically includes:
a vehicle detection model training step, namely marking a vehicle sample image, and training by using a deep learning algorithm based on the marked vehicle sample image to obtain a vehicle detection model;
and a license plate detection model training step, namely marking the external rectangle on the license plate sample image, and training the license plate sample image marked with the external rectangle in the vehicle detection model by using a deep learning algorithm to obtain a license plate detection model.
Still further, The deep learning algorithm is a Single Shot Detector (SSD) algorithm.
Still further, the one-shot detector algorithm is a Visual Geometry Group (VGG) convolutional neural network.
Further, the license plate detecting and positioning step specifically comprises:
a vehicle detection step, namely inputting the acquired vehicle image into a vehicle detection model to obtain vehicle information;
marking, namely marking a circumscribed rectangle of a license plate based on the vehicle information to obtain a license plate image with the circumscribed rectangle;
and a license plate detection step, namely inputting a license plate image with a circumscribed rectangle into a license plate detection model, and accurately positioning the license plate based on color and shape characteristics.
The invention also provides a license plate detection and positioning device, which comprises:
the sample image acquisition unit is used for acquiring a vehicle sample image and a license plate sample image;
and the sample image training unit is used for training the acquired vehicle sample image and the license plate sample image to obtain a license plate detection model.
The license plate detection positioning unit is used for acquiring a vehicle image and inputting the vehicle image into a license plate detection model to obtain the position of a license plate;
still further, the sample image training unit includes:
the vehicle detection model training unit is used for marking the vehicle sample images and training the marked vehicle sample images by using a deep learning algorithm to obtain a vehicle detection model;
and the license plate detection model training unit is used for marking the external rectangle on the license plate sample image, and training the license plate sample image marked with the external rectangle by using a deep learning algorithm in the vehicle detection model to obtain the license plate detection model.
Still further, The deep learning algorithm is a Single Shot Detector (SSD) algorithm.
Still further, the one-shot detector algorithm is a Visual Geometry Group (VGG) convolutional neural network.
Furthermore, the license plate detecting and positioning unit specifically comprises:
the vehicle detection unit is used for inputting the acquired vehicle image into a vehicle detection model to obtain vehicle information;
the marking unit is used for marking the external rectangle of the license plate based on the vehicle information to obtain a license plate image with the external rectangle;
and the license plate detection unit inputs the license plate image with the circumscribed rectangle into the license plate detection model and accurately positions the license plate based on the color and shape characteristics.
The invention also provides license plate detection and positioning equipment which is characterized by comprising a processor and a memory, wherein the processor is connected with the memory through a bus, machine readable codes are stored in the memory, and the processor executes the machine readable codes in the memory to execute any one of the methods.
The invention also relates to a computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program code which, when executed by a computer, can perform any of the methods described above.
The invention has the technical effects that: a vehicle and a license plate detection model are established based on an SSD model, a circumscribed rectangle of a license plate is marked based on vehicle information, and the accurate position of the license plate is further identified based on color and shape characteristics.
Drawings
FIG. 1 is a flow chart of a license plate detection and positioning method of the present invention.
Fig. 2 is a schematic structural diagram of a license plate detecting and positioning device of the present invention.
Fig. 3 is a schematic structural diagram of a license plate detecting and positioning device of the present invention.
Detailed Description
This is explained in detail below with reference to fig. 1-3.
Fig. 1 shows a license plate detection and positioning method of the present invention, which includes:
a license plate detection and positioning method comprises the following steps:
s11, acquiring a sample image, namely acquiring a vehicle sample image and a license plate sample image;
s12 sample image training step, training the obtained vehicle sample image and the license plate sample image to obtain a license plate detection model;
and S13 license plate detection and positioning, namely acquiring a vehicle image, and inputting the vehicle image into a license plate detection model to obtain the position of a license plate.
In step S11, the vehicle sample image and the license plate sample image may be obtained through a network and a shooting mode, and particularly, the vehicle sample image and the license plate sample image are collected from images at different angles and different positions to form a vehicle sample image and license plate sample image data packet, which may be stored in a storage medium, a server, or the like.
The sample image training step S12 includes:
a vehicle detection model training step, namely marking a vehicle sample image, and training by using a deep learning algorithm based on the marked vehicle sample image to obtain a vehicle detection model;
and a license plate detection model training step, namely marking the external rectangle on the license plate sample image, and training the license plate sample image marked with the external rectangle in the vehicle detection model by using a deep learning algorithm to obtain a license plate detection model.
In The training of vehicle detection models, The detection of vehicles is carried out by using marked vehicle samples, wherein a deep learning algorithm is used, specifically, a series of fixed-size bounding boxes are generated through an SSD model (SSD: The Single Shot Detector is based on a forward propagation CNN network), and The possibility that each box contains an object instance is that score, then a Non-maximum suppression (Non-maximum suppression) is carried out to obtain final predictions, and a VGG network is used for preliminary training, in the training process, parameter adjustment and sample adjustment are carried out according to the output of the loss function and the convergence condition of the result, the accuracy of the parameters is verified by using test data through a training data training model, and meanwhile, parameters are continuously modified by using a feedback network, so that final network convergence is achieved, and training of the vehicle detection model is completed. The training of the model can be training by using SSD under the caffe framework of Linux. The training of the license plate detection model is the same as that of the license plate detection model, and is not repeated.
The license plate detecting and positioning step S13 includes:
a vehicle detection step, namely inputting the acquired vehicle image into a vehicle detection model to obtain vehicle information;
marking, namely marking a circumscribed rectangle of a license plate based on the vehicle information to obtain a license plate image with the circumscribed rectangle;
and a license plate detection step, namely inputting a license plate image with a circumscribed rectangle into a license plate detection model, and accurately positioning the license plate based on color and shape characteristics.
In the vehicle detection step, the trained vehicle detection model is used for detecting the license plate in the vehicle, the SSD is used as the detection algorithm of the vehicle, the mark of the license plate is externally connected with a rectangle after the vehicle is detected, and the accuracy and the speed of the detection algorithm can achieve the expected effect.
In the license plate detection step, after the external rectangular mark of the license plate is finished, the accurate positioning of the license plate is realized by utilizing shape detection and color detection. Generally, the existing algorithm utilizes the bottom layer characteristics of an image to complete the positioning of a license plate, so the method is easily influenced by a background and a vehicle, the accuracy and the generalization are poor, and on the basis of realizing the accurate positioning of a license plate circumscribed rectangle under the model detection of deep learning, the real position positioning of the license plate is completed, so most background factor influences are eliminated, but certain difficulty still exists, and the algorithm based on the fusion of color and shape characteristics is designed. The process obtains a set which is in accordance with a specific shape in a parameter space by calculating the local maximum value of an accumulated result to be used as a Hough transformation result, and particularly maps curves or straight lines with the same shape in one space to a point in another coordinate space to form a peak value by using the transformation between the two coordinate spaces, thereby converting the problem of detecting any shape into a statistical peak value problem, and realizing the detection of the real edge of the license plate and connecting the detected straight lines. However, for the situation that the edge is covered, the position of the covered edge is calculated through the connected domain, the feature that the middle point of the circumscribed rectangle is overlapped with the middle point of the license plate is mainly utilized for processing, and the accurate positioning of the license plate is finally realized. Therefore, the specific operations of accurately positioning the license plate based on the color and shape features are as follows:
identifying a connected region of a license plate image with a circumscribed rectangle based on colors, and then determining the edge of the license plate after edge detection and Hough transformation;
and judging whether the edge of the license plate is covered or not, if not, determining the accurate position of the license plate based on the edge of the license plate, if so, determining the middle point of the edge of the license plate based on the middle point of the circumscribed rectangle, and determining the accurate position of the license plate based on the middle point of the edge of the license plate.
The precise position referred to by the invention has an error of less than 0.2 cm.
Fig. 2 shows that the invention of the present invention also provides a license plate detecting and positioning device, which comprises:
a sample image obtaining unit 21 that obtains a vehicle sample image and a license plate sample image;
the sample image training unit 22 is used for training the acquired vehicle sample images and license plate sample images to obtain a license plate detection model;
and the license plate detection positioning unit 23 is used for acquiring a vehicle image and inputting the vehicle image into the license plate detection model to obtain the position of the license plate.
The sample image obtaining unit 21 may obtain the vehicle sample image and the license plate sample image through a network and a shooting manner, and particularly, collects the vehicles in the images at different angles and different positions to form a vehicle sample image and a license plate sample image data packet, where the data packet may be stored in a storage medium, may be stored in a server, and so on.
The sample image training unit 22 includes:
the vehicle detection model training unit is used for marking the vehicle sample images and training the marked vehicle sample images by using a deep learning algorithm to obtain a vehicle detection model;
and the license plate detection model training unit is used for marking the external rectangle on the license plate sample image, and training the license plate sample image marked with the external rectangle by using a deep learning algorithm in the vehicle detection model to obtain the license plate detection model.
The sample image training unit 22, when performing vehicle detection model training, performs detection of a vehicle using the marked vehicle sample, here we use The algorithm of deep learning, specifically by means of SSD model (SSD: The Single Shot Detector is based on a forward propagation CNN network, generating a series of fixed-size bounding boxes, and The possibility of each box containing an object instance, i.e. score, followed by a Non-maximum suppression (Non-maximum suppression) to get The final predictions, using VGG network for preliminary training, in the training process, parameter adjustment and sample adjustment are carried out according to the output of the loss function and the convergence condition of the result, the accuracy of the parameters is verified by using test data through a training data training model, and meanwhile, parameters are continuously modified by using a feedback network, so that final network convergence is achieved, and training of the vehicle detection model is completed. The training of the license plate detection model is the same as that of the license plate detection model, and is not repeated.
The license plate detecting and positioning unit 23 includes:
the vehicle detection unit is used for inputting the acquired vehicle image into a vehicle detection model to obtain vehicle information;
the marking unit is used for marking the external rectangle of the license plate based on the vehicle information to obtain a license plate image with the external rectangle;
and the license plate detection unit inputs the license plate image with the circumscribed rectangle into the license plate detection model and accurately positions the license plate based on the color and shape characteristics.
When detecting the license plate, the license plate detection and positioning unit 23 completes the external rectangular marking of the license plate and then realizes the accurate positioning of the license plate by using shape detection and color detection. Generally, the existing algorithm utilizes the bottom layer characteristics of an image to complete the positioning of a license plate, so the method is easily influenced by a background and a vehicle, the accuracy and the generalization are poor, and on the basis of realizing the accurate positioning of a license plate circumscribed rectangle under the model detection of deep learning, the real position positioning of the license plate is completed, so most background factor influences are eliminated, but certain difficulty still exists, and the algorithm based on the fusion of color and shape characteristics is designed. The process obtains a set which is in accordance with a specific shape in a parameter space by calculating the local maximum value of an accumulated result to be used as a Hough transformation result, and particularly maps curves or straight lines with the same shape in one space to a point in another coordinate space to form a peak value by using the transformation between the two coordinate spaces, thereby converting the problem of detecting any shape into a statistical peak value problem, and realizing the detection of the real edge of the license plate and connecting the detected straight lines. However, for the situation that the edge is covered, the position of the covered edge is calculated through the connected domain, the feature that the middle point of the circumscribed rectangle is overlapped with the middle point of the license plate is mainly utilized for processing, and the accurate positioning of the license plate is finally realized. Therefore, the algorithm for accurately positioning the license plate based on the color and shape features is as follows:
identifying a connected region of a license plate image with a circumscribed rectangle based on colors, and then determining the edge of the license plate after edge detection and Hough transformation;
and judging whether the edge of the license plate is covered or not, if not, determining the accurate position of the license plate based on the edge of the license plate, if so, determining the middle point of the edge of the license plate based on the middle point of the circumscribed rectangle, and determining the accurate position of the license plate based on the middle point of the edge of the license plate.
Fig. 3 shows that the present invention also provides a license plate detecting and positioning device, which includes a processor 31, a memory 32 and a display screen 33, although the device may also include other components, such as a wifi module, a bluetooth module, a USB interface, and other interfaces that need to be used, which are not shown here. The processor 31 is respectively connected with the memory 32 and the display 33 through buses, the memory 32 can store programs and data executed by the device, and the processor 31 can execute the programs in the memory 32 and execute corresponding operations, such as the method shown in fig. 1. The device of the present invention may be a server, a desktop, a tablet, a notebook, etc., but is not limited to these devices.
The invention also relates to a computer-readable storage medium having stored thereon computer program code which, when executed by a computer, performs the method of fig. 1.
The method of the present invention may be implemented by a computer program, or the computer program may be stored in a storage medium, and a processor reads the computer program from the storage medium and executes the corresponding method.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made thereto without departing from the spirit and scope of the invention and it is intended to cover in the claims the invention as defined in the appended claims.
Claims (8)
1. A license plate detection and positioning method is characterized by comprising the following steps:
a sample image obtaining step, namely obtaining a vehicle sample image and a license plate sample image;
a sample image training step, wherein the obtained vehicle sample image and the license plate sample image are trained to obtain a license plate detection model;
the method comprises the following steps of detecting and positioning the license plate, namely acquiring a vehicle image, and inputting the vehicle image into a license plate detection model to obtain the position of the license plate;
the sample image training step specifically comprises:
a vehicle detection model training step, namely marking a vehicle sample image, and training by using a deep learning algorithm based on the marked vehicle sample image to obtain a vehicle detection model;
a license plate detection model training step, namely marking a circumscribed rectangle on a license plate sample image, and training the license plate sample image marked with the circumscribed rectangle in a vehicle detection model by using a deep learning algorithm to obtain a license plate detection model;
the license plate detecting and positioning step specifically comprises the following steps:
a vehicle detection step, namely inputting the acquired vehicle image into a vehicle detection model to obtain vehicle information;
marking, namely marking a circumscribed rectangle of a license plate based on the vehicle information to obtain a license plate image with the circumscribed rectangle;
a license plate detection step, namely inputting a license plate image with a circumscribed rectangle into a license plate detection model, and accurately positioning a license plate based on color and shape characteristics;
the specific operation of accurately positioning the license plate based on the color and shape characteristics is as follows: identifying a connected region of a license plate image with a circumscribed rectangle based on colors, and then determining the edge of the license plate after edge detection and Hough transformation; and judging whether the edge of the license plate is covered or not, if not, determining the accurate position of the license plate based on the edge of the license plate, if so, determining the middle point of the edge of the license plate based on the middle point of the circumscribed rectangle, and determining the accurate position of the license plate based on the middle point of the edge of the license plate.
2. The method of claim 1, wherein the deep learning algorithm is a one-shot detector algorithm.
3. The method of claim 2, wherein the one-shot detector algorithm is a visual geometry set convolutional neural network.
4. A license plate detects positioner, its characterized in that, the device includes:
the sample image acquisition unit is used for acquiring a vehicle sample image and a license plate sample image;
the sample image training unit is used for training the acquired vehicle sample image and the license plate sample image to obtain a license plate detection model;
the license plate detection positioning unit is used for acquiring a vehicle image and inputting the vehicle image into a license plate detection model to obtain the position of a license plate;
the sample image training unit includes:
the vehicle detection model training unit is used for marking the vehicle sample images and training the marked vehicle sample images by using a deep learning algorithm to obtain a vehicle detection model;
the license plate detection model training unit is used for marking the license plate sample image into a circumscribed rectangle, and training the license plate sample image marked with the circumscribed rectangle by using a deep learning algorithm in the vehicle detection model to obtain a license plate detection model;
the license plate detecting and positioning unit specifically comprises:
the vehicle detection unit is used for inputting the acquired vehicle image into a vehicle detection model to obtain vehicle information;
the marking unit is used for marking the external rectangle of the license plate based on the vehicle information to obtain a license plate image with the external rectangle;
the license plate detection unit inputs a license plate image with a circumscribed rectangle into a license plate detection model and accurately positions the license plate based on color and shape characteristics;
the specific operation of accurately positioning the license plate based on the color and shape characteristics is as follows: identifying a connected region of a license plate image with a circumscribed rectangle based on colors, and then determining the edge of the license plate after edge detection and Hough transformation; and judging whether the edge of the license plate is covered or not, if not, determining the accurate position of the license plate based on the edge of the license plate, if so, determining the middle point of the edge of the license plate based on the middle point of the circumscribed rectangle, and determining the accurate position of the license plate based on the middle point of the edge of the license plate.
5. The apparatus of claim 4, wherein the deep learning algorithm is a one-shot detector algorithm.
6. The apparatus of claim 5, wherein the one-shot detector algorithm is a visual geometry set convolutional neural network.
7. A license plate detection and location device, comprising a processor and a memory, wherein the processor is connected to the memory via a bus, the memory stores machine readable code, and the processor executes the machine readable code in the memory to perform the method of any one of claims 1-3.
8. A computer-readable storage medium, characterized in that the storage medium has stored thereon computer program code which, when executed by a computer, can perform the method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710300702.5A CN108805121B (en) | 2017-05-02 | 2017-05-02 | License plate detection and positioning method, device, equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710300702.5A CN108805121B (en) | 2017-05-02 | 2017-05-02 | License plate detection and positioning method, device, equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108805121A CN108805121A (en) | 2018-11-13 |
| CN108805121B true CN108805121B (en) | 2021-07-13 |
Family
ID=64054322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710300702.5A Active CN108805121B (en) | 2017-05-02 | 2017-05-02 | License plate detection and positioning method, device, equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805121B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726717B (en) * | 2019-01-02 | 2022-03-01 | 西南石油大学 | Vehicle comprehensive information detection system |
| CN110909742A (en) * | 2019-11-19 | 2020-03-24 | 上海眼控科技股份有限公司 | License plate detection method, system, platform and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413147A (en) * | 2013-08-28 | 2013-11-27 | 庄浩洋 | Vehicle license plate recognizing method and system |
| CN104751190A (en) * | 2015-04-23 | 2015-07-01 | 武汉大学 | Vehicle part positioning method for vehicle fine recognition |
| CN105046196A (en) * | 2015-06-11 | 2015-11-11 | 西安电子科技大学 | Front vehicle information structured output method base on concatenated convolutional neural networks |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043945B (en) * | 2010-11-23 | 2013-01-30 | 聊城大学 | License plate character recognition method based on real-time vehicle tracking and binary index classification |
| CN106203433A (en) * | 2016-07-13 | 2016-12-07 | 西安电子科技大学 | In a kind of vehicle monitoring image, car plate position automatically extracts and the method for perspective correction |
| CN106446150B (en) * | 2016-09-21 | 2019-10-29 | 北京数字智通科技有限公司 | A kind of method and device of vehicle precise search |
-
2017
- 2017-05-02 CN CN201710300702.5A patent/CN108805121B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413147A (en) * | 2013-08-28 | 2013-11-27 | 庄浩洋 | Vehicle license plate recognizing method and system |
| CN104751190A (en) * | 2015-04-23 | 2015-07-01 | 武汉大学 | Vehicle part positioning method for vehicle fine recognition |
| CN105046196A (en) * | 2015-06-11 | 2015-11-11 | 西安电子科技大学 | Front vehicle information structured output method base on concatenated convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| SSD: Single Shot MultiBox Detector;Wei Liu et al.;《Computer Vision - ECCV 2016》;20161231;第21-37页、图2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108805121A (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11422261B2 (en) | Robot relocalization method and apparatus and robot using the same | |
| CN109285220B (en) | Three-dimensional scene map generation method, device, equipment and storage medium | |
| CN110176078B (en) | Method and device for labeling training set data | |
| CN106707293A (en) | Obstacle recognition method and device for vehicles | |
| CN110929612A (en) | Target object labeling method, device and equipment | |
| CN109934847A (en) | The method and apparatus of weak texture three-dimension object Attitude estimation | |
| KR20200136723A (en) | Method and apparatus for generating learning data for object recognition using virtual city model | |
| CN112683169A (en) | Object size measuring method, device, equipment and storage medium | |
| CN112115820A (en) | Vehicle-mounted driving assisting method and device, computer device and readable storage medium | |
| CN111178170A (en) | Gesture recognition method and electronic equipment | |
| CN113469000A (en) | Regional map processing method and device, storage medium and electronic device | |
| CN108805121B (en) | License plate detection and positioning method, device, equipment and computer readable medium | |
| CN110942092B (en) | Graphic image recognition method and recognition system | |
| CN111091104A (en) | Target object protection detection method, device, equipment and storage medium | |
| CN112132845B (en) | Method, device, electronic equipment and readable medium for singulating three-dimensional model | |
| CN116778458B (en) | Parking space detection model construction method, parking space detection method, equipment and storage medium | |
| CN112528918A (en) | Road element identification method, map marking method and device and vehicle | |
| CN114627438A (en) | Target detection model generation method, target detection method, device and medium | |
| CN111723799A (en) | Coordinate positioning method, device, equipment and storage medium | |
| CN112927338B (en) | Simulation method based on three-dimensional profile, storage medium and computer equipment | |
| CN115565072A (en) | Road garbage recognition and positioning method and device, electronic equipment and medium | |
| CN114694257A (en) | Multi-user real-time three-dimensional action recognition and evaluation method, device, equipment and medium | |
| CN112308740A (en) | House area intelligent right adjusting method and system | |
| CN113806236B (en) | Method and system for one-machine multi-control of cloud real machine in mobile test field | |
| CN116665500A (en) | Engine test run simulation training full-task system and method based on virtual reality |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231218 Address after: 230012 In the factory building of Anhui Guogou Energy Co., Ltd., 100 meters east of the intersection of Guanjing Road and Luban Road in Xinzhan District, Hefei City, Anhui Province Patentee after: Hefei Youquan Information Technology Co.,Ltd. Address before: 100102 room 323701, building 5, yard 1, Futong East Street, Chaoyang District, Beijing Patentee before: YOUXINPAI (BEIJING) INFORMATION TECHNOLOGY Co.,Ltd. |