CN111860219A - High-speed road occupation judging method and device and electronic equipment - Google Patents
High-speed road occupation judging method and device and electronic equipment Download PDFInfo
- Publication number
- CN111860219A CN111860219A CN202010618919.2A CN202010618919A CN111860219A CN 111860219 A CN111860219 A CN 111860219A CN 202010618919 A CN202010618919 A CN 202010618919A CN 111860219 A CN111860219 A CN 111860219A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- training
- picture
- recognition model
- license plate
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 52
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- 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
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The invention discloses a high-speed lane occupation judging method, which relates to the technical field of road violation judgment and comprises the following steps: pre-training a vehicle detection model; inputting a picture of a vehicle to be detected to a vehicle detection model to search for a vehicle position, and identifying vehicle information; and judging whether the vehicle occupies the road according to the pre-defined coordinates. According to the scheme, the vehicle picture to be detected is brought in real time according to the pre-trained vehicle detection model, so that the vehicle picture identification precision is improved, and the identification efficiency is improved; meanwhile, the size of the received picture can be any, so that the limitation of the picture format is reduced; the whole process separates the steps of detection and classification, so that each network has more specificity, the advantages of each network are brought into play, and the result is more accurate. The invention also discloses a high-speed road occupation judging device and electronic equipment.
Description
Technical Field
The invention relates to the technical field of road violation judgment, in particular to a method and a device for judging high-speed road occupation and electronic equipment.
Background
The number of vehicles on the highway is large, the workload of manual illegal judgment is too large, and the work quality is easily reduced due to long-time work, so that the automatic judgment of the high-speed illegal is increasingly important. Many vehicle detection and license plate recognition systems are emerging in the market. The vehicle detection and license plate number recognition can be carried out according to the pictures shot by the road monitoring camera, and the warning and early warning are carried out on illegal road occupation vehicles. However, the existing method has insufficient precision due to the fact that the steps are not refined enough, so that each step can complete too many tasks. And the existing algorithm is mostly finished by adopting a convolutional neural network with a full connection layer, and needs input of a fixed scale, so that the precision is reduced if the size is changed.
The existing high-speed lane occupation judging system has the problem of insufficient precision, so that the false alarm rate of software is high. The main reasons are as follows.
1. The detection and the classification are carried out in the same network, and the detection network has the advantage of regression coordinates, so that no special classification network is strong in classification capacity.
2. The conventional detection network has a full connection layer, so that an image input with a fixed length is required, and if the length is inconsistent with a preset length, the zooming is stretched again, which causes distortion of a picture.
3. The traditional detection has no key point information, and because the accurate position of the vehicle head cannot be found through the perspective relation, misjudgment is easily caused.
Disclosure of Invention
In order to overcome the problems of insufficient precision and high false alarm rate of software in the prior art, the invention aims to provide a high-speed lane occupation judging method.
One of the purposes of the invention is realized by adopting the following technical scheme:
a high-speed lane occupation judging method comprises the following steps:
pre-training a vehicle detection model;
inputting a picture of a vehicle to be detected to a vehicle detection model to search for a vehicle position, and identifying vehicle information;
and judging whether the vehicle occupies the road according to the pre-defined coordinates.
Further, the pre-trained vehicle detection model comprises: the system comprises a pre-training vehicle position recognition model, a pre-training vehicle head corner point recognition model, a pre-training license plate number recognition model and a pre-training vehicle type recognition model.
Further, the vehicle position recognition model is pre-trained, and the process comprises the following steps:
acquiring a picture for training a vehicle, outputting each type of feature map including a background type and a vehicle type through a convolutional neural network layer, and outputting 5 feature maps in each type;
processing the feature maps, wherein the length of each feature map is 32 times of the length of the input pixel, and the width of the input image is 32 times of the width of the input pixel;
according to each processed feature map, each point in the feature map represents an area in the original map, so that each point can output coordinates and the probability of the center of each object, and the position coordinates and the confidence coefficient of the vehicle are calculated.
Further, the pre-training of the vehicle head corner point recognition model comprises the following steps:
obtaining a vehicle picture data set, outputting a 1024-dimensional feature vector through a convolutional neural network layer, obtaining the output of a 4n x 1-dimensional matrix through 4n vector multiplications, wherein n represents the number of angular points to be predicted, finally outputting a 4 n-dimensional vector, and each angular point represents four coordinates of x, y, w and h to obtain 4n results;
and presetting the output characteristic graph to be n × n, and the input characteristic graph to be w × h, dividing w × h pixel points into n × n blocks, and taking the maximum value of the pixel points in each block.
Further, the license plate number recognition model is pre-trained, and the process comprises the following steps:
acquiring a license plate picture data set, outputting (n +1) × 5 feature maps in each class through a convolution neural network, wherein n is the sum of all letters and provinces, namely the types, and outputting the position of each character and the corresponding character according to the position of the license plate.
Further, the license plate type recognition model is pre-trained, and the process comprises the following steps:
classifying the categories of the vehicle picture data set by using a classified convolutional neural network, and correspondingly marking the types;
and (4) bringing the classified vehicle picture data set into a resnet neural network for training to obtain a vehicle classification network model.
Further, identifying the vehicle information further includes: the license plate color is identified, and the process comprises the following steps:
acquiring a license plate picture to be detected, counting three histograms of RGB distribution of the picture, wherein the range is from 0 to 255, and finally summarizing the histograms into a 256 x 3-dimensional vector;
and inputting the vectors into an SVM for color classification to obtain the trained target color types.
Further, the step of judging whether the vehicle is occupied according to the pre-defined coordinates comprises the following steps:
dividing lane coordinates;
the method for acquiring the vehicle information and judging whether the vehicle occupies the lane comprises the following steps: and judging according to the vehicle information and the current lane coordinate position.
The invention also aims to provide a high-speed lane occupation judging device, which aims to improve the recognition efficiency of high-speed lane occupation judgment by adopting the training of a pre-trained vehicle position recognition model and adopting a recognition process taking the corner point of a vehicle head as a base point.
The second purpose of the invention is realized by adopting the following technical scheme:
an expressway occupation judging device comprising:
the pre-training module is used for generating a pre-training vehicle position recognition model, a pre-training vehicle head corner point recognition model, a pre-training license plate number recognition model and a pre-training vehicle type recognition model;
the vehicle searching module is used for searching the position of a vehicle according to the input picture of the vehicle to be detected to the vehicle detection model and identifying the vehicle information;
and the illegal judgment module judges whether the vehicle occupies the road or not according to the pre-defined coordinates.
It is a further object of the present invention to provide an electronic device, which includes a processor, a storage medium, and a computer program, wherein the computer program is stored in the storage medium, and when the computer program is executed by the processor, the method for determining a high-speed lane occupation is implemented.
Compared with the prior art, the invention has the beneficial effects that:
the size of the received picture can be any, so that the limitation of the picture format is reduced; meanwhile, the whole process separates the steps of detection and classification, so that each network has more specificity, the advantages of each network are brought into play, and the result is more accurate.
Drawings
FIG. 1 is a schematic flow chart of the operation of the present invention;
FIG. 2 is a schematic diagram of the effect of a feature map output by a pre-trained vehicle position recognition model after passing through a convolutional neural network layer in the present invention;
FIG. 3 is a schematic diagram of the effect of a feature map output by a pre-trained vehicle head corner point identification model after passing through a convolutional neural network layer in the invention;
FIG. 4 is a schematic diagram of a characteristic diagram effect output by a pre-training vehicle corner point recognition model according to a preset size in the invention;
FIG. 5 is a block diagram of an apparatus for determining an expressway occupation, according to the present invention;
fig. 6 is a block diagram of an electronic device according to a third embodiment.
Detailed Description
The present invention will now be described in more detail with reference to the accompanying drawings, in which the description of the invention is given by way of illustration and not of limitation. The various embodiments may be combined with each other to form other embodiments not shown in the following description.
Example one
The embodiment provides a method for judging high-speed lane occupation, which aims to improve the identification efficiency of high-speed lane occupation judgment by adopting training of a pre-trained vehicle position identification model and adopting an identification process taking a head corner point as a base point.
According to the above principle, a method for determining a high-speed lane occupation is introduced, as shown in fig. 1, including the following steps:
pre-training a vehicle detection model;
inputting a picture of a vehicle to be detected to a vehicle detection model to search for a vehicle position, and identifying vehicle information;
and judging whether the vehicle occupies the road according to the pre-defined coordinates.
The size of the received picture can be any, so that the limitation of the picture format is reduced; meanwhile, the whole process separates the steps of detection and classification, so that each network has more specificity, the advantages of each network are brought into play, and the result is more accurate.
In this embodiment, the pre-training vehicle detection model includes: the system comprises a pre-training vehicle position recognition model, a pre-training vehicle head corner point recognition model, a pre-training license plate number recognition model and a pre-training vehicle type recognition model. Through the prediction model training, a target result can be quickly obtained by substituting the trained prediction model into the to-be-detected picture data, and the recognition accuracy is improved according to task division.
Pre-training a vehicle position recognition model, the process comprising:
acquiring a picture for training a vehicle, outputting each type of feature map including a background type and a vehicle type through a convolutional neural network layer, and outputting 5 feature maps in each type;
Processing the feature maps, wherein the length of each feature map is 32 times of the length of the input pixel, and the width of the input image is 32 times of the width of the input pixel;
according to each processed feature map, each point in the feature map represents an area in the original map, so that each point can output coordinates and the probability of the center of each object, and the position coordinates and the confidence of the vehicle are calculated, as shown in fig. 2.
In this embodiment, for example, if the original image is input as a 64 × 64 graph, 10 feature graphs of 2 × 2 including the background and the vehicle are output; the feature map is calculated and scaled from the original image, so each point represents an area in the original image, and each point outputs the probability and coordinates of the center of each object. The common vehicle and background 2 categories, each category outputting four coordinates x, y, w, h and a confidence level representing the probability of being an object of this type. So 2 x 5 x 2 numbers are finally output for finding the position of the object to be found.
Pre-training a vehicle head corner point identification model, wherein the process comprises the following steps:
as shown in fig. 3 to 4, a vehicle image data set is obtained, a 1024-dimensional feature vector is output through a convolutional neural network layer, and output of a 4n x 1-dimensional matrix is obtained through multiplication of 4n vectors, where n represents the number of corner points to be predicted, and finally a 4 n-dimensional vector is output, and each corner point represents four coordinates of x, y, w, and h, so that 4n results are obtained;
And presetting the output characteristic graph to be n × n, and the input characteristic graph to be w × h, dividing w × h pixel points into n × n blocks, and taking the maximum value of the pixel points in each block.
In this embodiment, the fully-connected layer is connected to a spatial pyramid pooling layer, and the purpose of the fully-connected layer is to convert a feature map of any size into a feature map of a fixed size, so as to meet the requirement of input of the fully-connected layer of the next layer.
The pre-training license plate number recognition model comprises the following processes:
acquiring a license plate picture data set, outputting (n +1) × 5 feature maps in each class through a convolution neural network, wherein n is the sum of all letters and provinces, namely the types, and outputting the position of each character and the corresponding character according to the position of the license plate.
The pre-training license plate type recognition model comprises the following processes:
classifying the categories of the vehicle picture data set by using a classified convolutional neural network, and correspondingly marking the types;
and (4) bringing the classified vehicle picture data set into a resnet neural network for training to obtain a vehicle classification network model.
In the embodiment, through the vehicle classification network model, whether subsequent road occupation is illegal or not can be judged according to the recognized vehicle pictures, such as three types of vehicles including a passenger car, a truck and a trolley;
identifying the vehicle information further includes: the license plate color is identified, and the process comprises the following steps:
acquiring a license plate picture to be detected, counting three histograms of RGB distribution of the picture, wherein the range is from 0 to 255, and finally summarizing the histograms into a 256 x 3-dimensional vector;
and inputting the vectors into an SVM for color classification to obtain the trained target color types.
In this embodiment, the color of the license plate, such as blue, green, yellow, and white, is determined to correspond to the license plate color to the lane occupation right and the identification.
Judging whether the vehicle is occupied according to the pre-defined coordinates, wherein the step comprises the following steps of:
dividing lane coordinates;
the method for acquiring the vehicle information and judging whether the vehicle occupies the lane comprises the following steps: and judging according to the vehicle information and the current lane coordinate position.
In this embodiment, the information of the vehicle is collected and acquired, and then the judgment is performed according to the vehicle information and the current vehicle position information, if the bus cannot run on the express way, it is determined that the bus illegally occupies the lane, and the vehicle information of the vehicle photo is recorded at the same time.
Example two
The second embodiment discloses a high-speed lane occupation judging device corresponding to the first embodiment, which is a virtual device structure of the first embodiment, and as shown in fig. 5, the high-speed lane occupation judging device includes:
an expressway occupation judging device comprising:
the pre-training module 210 is used for generating a pre-training vehicle position identification model, a pre-training vehicle head corner point identification model, a pre-training license plate number identification model and a pre-training vehicle type identification model;
the vehicle searching module 220 searches the vehicle position according to the input vehicle picture to be detected to the vehicle detection model and identifies the vehicle information;
and the illegal judging module 230 judges whether the vehicle occupies the road according to the pre-defined coordinates.
EXAMPLE III
Fig. 6 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention, where the electronic device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of the processors 310 in the computer device may be one or more, and one processor 310 is taken as an example in fig. 5; the processor 310, the memory 320, the input device 330 and the output device 340 in the electronic apparatus may be connected by a bus or other means, and fig. 6 illustrates an example of connection by a bus. The memory 320 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to a method for determining an occupied road at high speed in the second embodiment of the present invention (for example, the pre-training module 210, the vehicle searching module 220, and the illegal determining module 230 in an apparatus for determining an occupied road at high speed). The processor 310 executes various functional applications and data processing of the electronic device by executing software programs, instructions and modules stored in the memory 320, so as to implement a high-speed lane occupation judgment method according to the first embodiment. The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 320 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 320 may further include memory located remotely from the processor 310, which may be connected to the electronic device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 330 may be used to receive input information, etc. The output device 340 may be a display device such as a display screen, and may be used to display alarm information.
It should be noted that, in the embodiment of the above-mentioned expressway occupation determination apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. A high-speed lane occupation judging method is characterized by comprising the following steps:
pre-training a vehicle detection model;
inputting a picture of a vehicle to be detected to a vehicle detection model to search for a vehicle position, and identifying vehicle information;
and judging whether the vehicle occupies the road according to the pre-defined coordinates.
2. The high-speed lane-occupying judging method according to claim 1, wherein: the pre-trained vehicle detection model comprises: the system comprises a pre-training vehicle position recognition model, a pre-training vehicle head corner point recognition model, a pre-training license plate number recognition model and a pre-training vehicle type recognition model.
3. The high-speed lane-occupying judging method according to claim 2, wherein: pre-training a vehicle position recognition model, the process comprising:
acquiring a picture for training a vehicle, outputting each type of feature map including a background type and a vehicle type through a convolutional neural network layer, and outputting 5 feature maps in each type;
processing the feature maps, wherein the length of each feature map is 32 times of the length of the input pixel, and the width of the input image is 32 times of the width of the input pixel;
according to each processed feature map, each point in the feature map represents an area in the original map, so that each point can output coordinates and the probability of the center of each object, and the position coordinates and the confidence coefficient of the vehicle are calculated.
4. The high-speed lane-occupying judging method according to claim 2, wherein: pre-training a vehicle head corner point identification model, wherein the process comprises the following steps:
obtaining a vehicle picture data set, outputting a 1024-dimensional feature vector through a convolutional neural network layer, obtaining the output of a 4n x 1-dimensional matrix through 4n vector multiplications, wherein n represents the number of angular points to be predicted, finally outputting a 4 n-dimensional vector, and each angular point represents four coordinates of x, y, w and h to obtain 4n results;
and presetting the output characteristic graph to be n × n, and the input characteristic graph to be w × h, dividing w × h pixel points into n × n blocks, and taking the maximum value of the pixel points in each block.
5. The high-speed lane-occupying judging method according to claim 2, wherein: the pre-training license plate number recognition model comprises the following processes:
acquiring a license plate picture data set, outputting (n +1) × 5 feature maps in each class through a convolution neural network, wherein n is the sum of all letters and provinces, namely the types, and outputting the position of each character and the corresponding character according to the position of the license plate.
6. The high-speed lane-occupying judging method according to claim 2, wherein: the pre-training license plate type recognition model comprises the following processes:
classifying the categories of the vehicle picture data set by using a classified convolutional neural network, and correspondingly marking the types;
and (4) bringing the classified vehicle picture data set into a resnet neural network for training to obtain a vehicle classification network model.
7. The high-speed lane-occupying judging method according to claim 1, wherein: identifying the vehicle information further includes: the license plate color is identified, and the process comprises the following steps:
acquiring a license plate picture to be detected, counting three histograms of RGB distribution of the picture, wherein the range is from 0 to 255, and finally summarizing the histograms into a 256 x 3-dimensional vector;
and inputting the vectors into an SVM for color classification to obtain the trained target color types.
8. The high-speed lane-occupying judging method according to claim 1, wherein: judging whether the vehicle is occupied according to the pre-defined coordinates, wherein the step comprises the following steps of:
dividing lane coordinates;
the method for acquiring the vehicle information and judging whether the vehicle occupies the lane comprises the following steps: and judging according to the vehicle information and the current lane coordinate position.
9. A high-speed lane occupancy determination system according to any one of claims 1 to 8, comprising:
the pre-training module is used for generating a pre-training vehicle position recognition model, a pre-training vehicle head corner point recognition model, a pre-training license plate number recognition model and a pre-training vehicle type recognition model;
the vehicle searching module is used for searching the position of a vehicle according to the input picture of the vehicle to be detected to the vehicle detection model and identifying the vehicle information;
and the illegal judgment module judges whether the vehicle occupies the road or not according to the pre-defined coordinates.
10. An electronic device comprising a processor, a storage medium, and a computer program, the computer program being stored in the storage medium, wherein the computer program, when executed by the processor, performs a high-speed lane occupancy determination method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618919.2A CN111860219B (en) | 2020-06-30 | 2020-06-30 | High-speed channel occupation judging method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618919.2A CN111860219B (en) | 2020-06-30 | 2020-06-30 | High-speed channel occupation judging method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111860219A true CN111860219A (en) | 2020-10-30 |
| CN111860219B CN111860219B (en) | 2024-01-05 |
Family
ID=72989401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010618919.2A Active CN111860219B (en) | 2020-06-30 | 2020-06-30 | High-speed channel occupation judging method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860219B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818834A (en) * | 2021-01-29 | 2021-05-18 | 山东大学 | Method, device and medium for judging avoidance of emergency vehicle at intersection |
| CN114882492A (en) * | 2022-07-11 | 2022-08-09 | 浙江大华技术股份有限公司 | License plate recognition method, device, terminal and computer readable storage medium |
| CN116704467A (en) * | 2023-08-04 | 2023-09-05 | 哪吒港航智慧科技(上海)有限公司 | Automatic identification method, device and equipment for preventing vehicles from being crashed and storage medium |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003084064A (en) * | 2001-09-12 | 2003-03-19 | Daihatsu Motor Co Ltd | Device and method for recognizing vehicle in front side |
| CN103268471A (en) * | 2013-04-17 | 2013-08-28 | 深圳市锐明视讯技术有限公司 | Vehicle illegal land occupying detection method and device |
| CN104063712A (en) * | 2014-06-27 | 2014-09-24 | 杭州科度科技有限公司 | Vehicle information extraction method and system thereof |
| 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 |
| CN105912979A (en) * | 2016-03-30 | 2016-08-31 | 浙江大华技术股份有限公司 | Vehicle on-road detection method and device |
| CN106203330A (en) * | 2016-07-08 | 2016-12-07 | 西安理工大学 | A kind of vehicle classification method based on convolutional neural networks |
| WO2017125063A1 (en) * | 2016-01-20 | 2017-07-27 | 中兴通讯股份有限公司 | Processing method and device for vehicle traffic violation |
| CN108171112A (en) * | 2017-12-01 | 2018-06-15 | 西安电子科技大学 | Vehicle identification and tracking based on convolutional neural networks |
| CN109145928A (en) * | 2017-06-16 | 2019-01-04 | 杭州海康威视数字技术股份有限公司 | It is a kind of based on the headstock of image towards recognition methods and device |
| WO2019019525A1 (en) * | 2017-07-24 | 2019-01-31 | 图灵通诺（北京）科技有限公司 | Convolutional neural network-based method and device for settlement of image recognition technology |
| CN109598943A (en) * | 2018-12-30 | 2019-04-09 | 北京旷视科技有限公司 | The monitoring method of vehicle violation, apparatus and system |
| CN109711264A (en) * | 2018-11-30 | 2019-05-03 | 武汉烽火众智智慧之星科技有限公司 | A kind of bus zone road occupying detection method and device |
| CN110210303A (en) * | 2019-04-29 | 2019-09-06 | 山东大学 | A kind of accurate lane of Beidou vision fusion recognizes and localization method and its realization device |
| CN110633712A (en) * | 2019-09-17 | 2019-12-31 | 中控智慧科技股份有限公司 | Method, system and device for recognizing vehicle body color and computer readable medium |
| EP3599572A1 (en) * | 2018-07-27 | 2020-01-29 | JENOPTIK Traffic Solutions UK Ltd | Method and apparatus for recognizing a license plate of a vehicle |
| CN110751037A (en) * | 2019-09-17 | 2020-02-04 | 中控智慧科技股份有限公司 | Method for recognizing color of vehicle body and terminal equipment |
| CN111259706A (en) * | 2018-12-03 | 2020-06-09 | 初速度（苏州）科技有限公司 | Lane line pressing judgment method and system for vehicle |
-
2020
- 2020-06-30 CN CN202010618919.2A patent/CN111860219B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003084064A (en) * | 2001-09-12 | 2003-03-19 | Daihatsu Motor Co Ltd | Device and method for recognizing vehicle in front side |
| CN103268471A (en) * | 2013-04-17 | 2013-08-28 | 深圳市锐明视讯技术有限公司 | Vehicle illegal land occupying detection method and device |
| CN104063712A (en) * | 2014-06-27 | 2014-09-24 | 杭州科度科技有限公司 | Vehicle information extraction method and system thereof |
| 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 |
| WO2017125063A1 (en) * | 2016-01-20 | 2017-07-27 | 中兴通讯股份有限公司 | Processing method and device for vehicle traffic violation |
| CN105912979A (en) * | 2016-03-30 | 2016-08-31 | 浙江大华技术股份有限公司 | Vehicle on-road detection method and device |
| CN106203330A (en) * | 2016-07-08 | 2016-12-07 | 西安理工大学 | A kind of vehicle classification method based on convolutional neural networks |
| CN109145928A (en) * | 2017-06-16 | 2019-01-04 | 杭州海康威视数字技术股份有限公司 | It is a kind of based on the headstock of image towards recognition methods and device |
| WO2019019525A1 (en) * | 2017-07-24 | 2019-01-31 | 图灵通诺（北京）科技有限公司 | Convolutional neural network-based method and device for settlement of image recognition technology |
| CN108171112A (en) * | 2017-12-01 | 2018-06-15 | 西安电子科技大学 | Vehicle identification and tracking based on convolutional neural networks |
| EP3599572A1 (en) * | 2018-07-27 | 2020-01-29 | JENOPTIK Traffic Solutions UK Ltd | Method and apparatus for recognizing a license plate of a vehicle |
| CN109711264A (en) * | 2018-11-30 | 2019-05-03 | 武汉烽火众智智慧之星科技有限公司 | A kind of bus zone road occupying detection method and device |
| CN111259706A (en) * | 2018-12-03 | 2020-06-09 | 初速度（苏州）科技有限公司 | Lane line pressing judgment method and system for vehicle |
| CN109598943A (en) * | 2018-12-30 | 2019-04-09 | 北京旷视科技有限公司 | The monitoring method of vehicle violation, apparatus and system |
| CN110210303A (en) * | 2019-04-29 | 2019-09-06 | 山东大学 | A kind of accurate lane of Beidou vision fusion recognizes and localization method and its realization device |
| CN110633712A (en) * | 2019-09-17 | 2019-12-31 | 中控智慧科技股份有限公司 | Method, system and device for recognizing vehicle body color and computer readable medium |
| CN110751037A (en) * | 2019-09-17 | 2020-02-04 | 中控智慧科技股份有限公司 | Method for recognizing color of vehicle body and terminal equipment |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818834A (en) * | 2021-01-29 | 2021-05-18 | 山东大学 | Method, device and medium for judging avoidance of emergency vehicle at intersection |
| CN114882492A (en) * | 2022-07-11 | 2022-08-09 | 浙江大华技术股份有限公司 | License plate recognition method, device, terminal and computer readable storage medium |
| CN114882492B (en) * | 2022-07-11 | 2022-11-22 | 浙江大华技术股份有限公司 | License plate recognition method, device, terminal and computer readable storage medium |
| CN116704467A (en) * | 2023-08-04 | 2023-09-05 | 哪吒港航智慧科技(上海)有限公司 | Automatic identification method, device and equipment for preventing vehicles from being crashed and storage medium |
| CN116704467B (en) * | 2023-08-04 | 2023-11-03 | 哪吒港航智慧科技(上海)有限公司 | Automatic identification method, device and equipment for preventing vehicles from being crashed and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111860219B (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| WO2021051601A1 (en) | Method and system for selecting detection box using mask r-cnn, and electronic device and storage medium | |
| CN111860219B (en) | High-speed channel occupation judging method and device and electronic equipment | |
| CN109740420A (en) | Vehicle illegal recognition methods and Related product | |
| CN110751012B (en) | Target detection evaluation method and device, electronic equipment and storage medium | |
| CN109993138A (en) | A kind of car plate detection and recognition methods and device | |
| CN111931683B (en) | Image recognition method, device and computer readable storage medium | |
| CN112613344B (en) | Vehicle track occupation detection method, device, computer equipment and readable storage medium | |
| CN112016605A (en) | Target detection method based on corner alignment and boundary matching of bounding box | |
| CN108960074B (en) | Small-size pedestrian target detection method based on deep learning | |
| CN110909598A (en) | Deep learning-based method for recognizing illegal traffic driving of non-motor vehicle lane | |
| CN108537223B (en) | License plate detection method, system and equipment and storage medium | |
| CN111753592A (en) | Traffic sign recognition method, traffic sign recognition device, computer equipment and storage medium | |
| CN117218622A (en) | Road condition detection method, electronic equipment and storage medium | |
| CN114821519A (en) | Traffic sign identification method and system based on coordinate attention | |
| CN110889388A (en) | Violation identification method, device, equipment and storage medium | |
| CN113297939A (en) | Obstacle detection method, system, terminal device and storage medium | |
| CN116069801B (en) | Traffic video structured data generation method, device and medium | |
| CN114898306B (en) | Method and device for detecting target orientation and electronic equipment | |
| CN113591543B (en) | Traffic sign recognition method, device, electronic equipment and computer storage medium | |
| CN115546762A (en) | Image clustering method, device, storage medium and server | |
| CN111709377B (en) | Feature extraction method, target re-identification method and device and electronic equipment | |
| CN114724128A (en) | License plate recognition method, device, equipment and medium | |
| CN110895692B (en) | Vehicle brand identification method and device and readable storage medium | |
| CN114119953A (en) | Method for quickly positioning and correcting license plate, storage medium and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |