CN109934161A - Vehicle identification and detection method and system based on convolutional neural network - Google Patents
Vehicle identification and detection method and system based on convolutional neural network Download PDFInfo
- Publication number
- CN109934161A CN109934161A CN201910182868.0A CN201910182868A CN109934161A CN 109934161 A CN109934161 A CN 109934161A CN 201910182868 A CN201910182868 A CN 201910182868A CN 109934161 A CN109934161 A CN 109934161A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- convolutional neural
- video
- monitoring
- motion state
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a vehicle identification and detection method and system based on a convolutional neural network, which is characterized by comprising the following steps of: extracting a vehicle picture sample and marking; carrying out region segmentation and type analysis training on the marked picture sample; extracting a group of random continuous images to be identified in a video to be identified; predicting the positions and the types of the vehicles in all the images to be recognized; outputting the motion state of the vehicle; the invention adopts a vehicle identification system to carry out intelligent and automatic management on related vehicles, controls and manages urban traffic by adopting a modern technical means, masters the running state of each vehicle in real time, can conveniently realize vehicle scheduling, can guide the rescue vehicle to track and dispose when danger occurs, and lays a solid foundation for timely leading and efficient monitoring of management departments.
Description
Technical field
The present invention relates to vehicle identification and administrative skill field more particularly to a kind of vehicle knowledges based on convolutional neural networks
Not with detection method and system.
Background technique
With the rapid development of social economy, the automobile quantity of every country main cities is growing day by day, and rule-breaking vehicle stops
Put is to lead to one of great reason of traffic congestion, therefore every country is all by corresponding laws and regulations clearly stipulate that in spy
Determining place, place and road, no parking, and traffic department mainly takes artificial progress to the supervision for parking behavior in violation of rules and regulations at present
The mode of patrol, therefore the supervision for park in violation of rules and regulations by way of manually going on patrol needs a large amount of manpower and material resources, it is few
A equipment can meet the requirement of real-time, accuracy and validity simultaneously.
In addition to this, special vehicles such as tank truck, Transportation of Dangerous Chemicals vehicle, dump truck, army's police car in recent years
Owning amount is also continuous therewith to be increased, and in order to be determined to the vehicle location in traveling, is widely used by using from GPS
The electric wave signal of (Global Positioning System: global positioning system) is come the method that is positioned.But this benefit
The error for containing tens meters or so with the precision that GPS positions vehicle is difficult true with the detailed position of higher precision progress
Fixed, therefore, traditional special vehicle management mode has been difficult to meet actual needs, and supervisory efficiency is low, and there are security risks.
Based on the traffic information collection of video image processing as a kind of important detection technique, by both domestic and external wide
General attention, with the development of social economy and the progress of science and technology, video detection technology also achieves swift and violent development, video
Testing product has been in high definition developing stage, at present city after it experienced simulation, digital two important development stages now
Field has had already appeared HD video testing product, and traffic video detection sensor is by being located at the video capture device above road
Traffic scene image is obtained, the technologies Automatic analysis scene figure such as Computer Image Processing, artificial intelligence, pattern-recognition is utilized
As information, to obtain traffic information.Since it is a kind of contactless traffic information collection equipment, vehicle can not influenced
Installation, debugging and the maintenance that equipment is carried out under operating condition, without closed section, meanwhile, video detection sensor can be same
When detect multiple lanes and carry out traffic monitoring under wide area scene, have at low cost, information comprehensively intuitive, easy to maintain and peace
The features such as dress, thus it is with high application prospect in intelligent transportation system.
Summary of the invention
The technical problem to be solved by the present invention is to overcome the deficiencies in the prior art, provide a kind of based on convolution mind
Vehicle identification and detection method and system through network.
The present invention is to be achieved by the following technical programs:
A kind of vehicle identification and detection method based on convolutional neural networks, which comprises the following steps:
A. the picture sample for extracting one group of variety classes vehicle specific modality carries out all categories vehicle in picture sample
Label；
B. marked picture sample is subjected to region segmentation and floristic analysing training using mask-rcnn；
C. communication connection is established with video monitoring end, extracts the images to be recognized of one group of random continuous in video to be identified；
D. vehicle location and type in all images to be recognized are predicted by mask-rcnn semantic segmentation；
E. the motion state of vehicle is exported by the motion tracking of video；
F. motion state is bound into vehicle monitoring service logic, output monitoring result and instruction.
According to the above technical scheme, it is preferable that the images to be recognized is the period extracted at random in video to be identified
The one group of image inside continuously chosen.
According to the above technical scheme, it is preferable that step e includes: to track the to be identified of consecutive frame by object tracking algorithm
All vehicle locations in image；The motion state of vehicle is exported according to car tracing situation.
According to the above technical scheme, it is preferable that step f include: when vehicle specific region motion state be it is static when, to
Monitoring client, which is sent, reminds instruction.
According to the above technical scheme, it is preferable that step f includes: when the quiescent time of vehicle being more than preset duration, to prison
It controls end and sends prompting instruction.
A kind of vehicle identification and detection system based on convolutional neural networks characterized by comprising marking unit is used
In the picture sample for extracting one group of variety classes vehicle specific modality, all categories vehicle in picture sample is marked；Instruction
Practice unit, for using mask-rcnn that marked picture sample is carried out region segmentation and floristic analysing training；It extracts single
Member extracts the images to be recognized of one group of random continuous in video to be identified for establishing communication connection with video monitoring end；Vehicle
Information identificating unit, for predicting vehicle location and type in all images to be recognized by mask-rcnn semantic segmentation；
Vehicle movement recognition unit exports the motion state of vehicle for the motion tracking by video；Monitoring unit, for that will move
State binds vehicle monitoring service logic, output monitoring result and instruction.
According to the above technical scheme, it is preferable that the vehicle movement recognition unit includes: tracing module, for passing through object
Body tracing algorithm tracks all vehicle locations in the images to be recognized of consecutive frame；Output module, for according to car tracing situation
Export the motion state of vehicle.
According to the above technical scheme, it is preferable that the monitoring unit includes: first judgment module, for when vehicle is in spy
Determine regional movement state be it is static when, to monitoring client send remind instruction.
According to the above technical scheme, it is preferable that the monitoring unit includes: the second judgment module, for working as the quiet of vehicle
When only the time is more than preset duration, is sent to monitoring client and remind instruction.
The beneficial effects of the present invention are:
The image recorded by video monitoring end extracts video clip and carries out discriminance analysis, passes through the motion tracking of video
Information command is transferred to vehicle prison by Internet to the vehicle-state for meeting specified conditions by the motion state for identifying vehicle
Administrative center is controlled, intelligent, automatic management is carried out to associated vehicle using vehicle identification system, for using up to date technics
Means control and management urban transportation, control the operating status of each car in real time, can facilitate realization vehicle scheduling, occur in danger
When, emergency car tracking and disposition can be guided, administrative department is dredged in time, efficiently monitoring is laid a solid foundation.
Detailed description of the invention
Fig. 1 is course of work schematic diagram of the invention.
Specific embodiment
In order to make those skilled in the art more fully understand technical solution of the present invention, with reference to the accompanying drawing and most
The present invention is described in further detail for good embodiment.
As shown, the invention discloses a kind of vehicle identification and detection method based on convolutional neural networks,
It is characterized in that, comprising the following steps: a. extracts the picture sample of one group of variety classes vehicle specific modality, will be complete in picture sample
Portion's type vehicle is marked, and interception is finely marked using VIA image component labeling algorithm frame contains various vehicle specific modalities
Picture sample in all vehicles profile, form the profile that the polygon of multiple closures surrounds, while marked vehicle kind class name
Claim, and the information of label is exported into json file；B. marked picture sample is subjected to region segmentation using mask-rcnn
It is trained with floristic analysing, mask-rcnn algorithm training json paper sample under tensorflow frame is used in this example；C. with view
Frequency monitoring client establishes communication connection, extracts the images to be recognized of one group of random continuous in video to be identified, the video prison in this example
Control end can be monitoring camera, can also be the video of satellite shooting for monitoring whether common vehicle invades specific region,
For monitoring the motion state of special vehicle in different environments；D. it is predicted by mask-rcnn semantic segmentation and needs to be known
Vehicle location and type in other image；E. the motion state of vehicle is exported by the motion tracking of video；F. by motion state
Bind vehicle monitoring service logic, output monitoring result and instruction.The image recorded by video monitoring end extracts video clip
Discriminance analysis is carried out, the motion state of vehicle is identified by the motion tracking of video, it is logical to the vehicle-state for meeting specified conditions
It crosses Internet and information command is transferred to vehicle monitoring management center, intelligence is carried out to associated vehicle using vehicle identification system
Change, automatic management, for urban transportation is controlled and managed using up to date technics means, controls the operation shape of each car in real time
State can facilitate realization vehicle scheduling, when danger occurs, can guide emergency car tracking and disposition, dredge in time to administrative department
It leads, efficiently monitoring is laid a solid foundation.
According to above-described embodiment, it is preferable that the images to be recognized is in the period extracted at random in video to be identified
The one group of image continuously chosen imports video to be identified using image algorithm frame opencv in this example, extracts from this video
The period of certain period of time, extraction is related with observing time with arithmetic speed, can be connected at random with endless but cannot be too short
It is continuous to choose one group of image as images to be recognized.
According to above-described embodiment, it is preferable that step e includes: the figure to be identified for tracking consecutive frame by object tracking algorithm
All vehicle locations as in observe all vehicle locations of consecutive frame image, utilize square since the first frame in images to be recognized
Battle array algorithm calculates the mass center where each vehicle's contour, using the mass center of each vehicle of first image as the center of circle, with presetted pixel
It is successively searched for for radius, checks each vehicle movement situation in the next frame, the shape difference of object where judgment object and mass center
Whether in a certain range, if it is think that current object is the object that object where a upper image centroid generates after displacement
Body, it is on the contrary then be considered inhomogeneity vehicle；The motion state that vehicle is exported according to car tracing situation, if within a certain period of time
Same vehicle centroid does not move, then it is assumed that the vehicle remains static.
According to above-described embodiment, it is preferable that step f includes: when vehicle is when specific region motion state is static, to prison
It controls end and sends prompting instruction, when vehicle is when taboo off-position is set and remains static, system sends to remind and instruct into traffic administration
The heart enables traffic administration person quickly to judge the motion state of vehicle, can improve the intelligent level of traffic surveillance videos, is traffic
Manager provides timely, effective accident treatment means and foundation.
According to above-described embodiment, it is preferable that step f includes: when the quiescent time of vehicle being more than preset duration, to monitoring
End, which is sent, reminds instruction, reasonable stationary vehicle duration alarm threshold value is arranged, when special vehicle stops in certain specific environments
When time is more than alarm threshold value, system sends to monitoring client and reminds instruction, convenient for controlling the operating status of each car in real time, is endangering
When danger occurs, emergency car tracking and disposition can be guided, administrative department is dredged in time, efficiently monitoring is laid a solid foundation.
The invention also discloses a kind of vehicle identification and detection system based on convolutional neural networks, which is characterized in that packet
It includes: marking unit, for extracting the picture sample of one group of variety classes vehicle specific modality, by all categories vehicle in picture sample
It is marked；Training unit, for using mask-rcnn that marked picture sample is carried out region segmentation and floristic analysing
Training；Extraction unit, for establishing communication connection with video monitoring end, extract in video to be identified one group of random continuous wait know
Other image；Information of vehicles recognition unit, for predicting vehicle position in all images to be recognized by mask-rcnn semantic segmentation
It sets and type；Vehicle movement recognition unit exports the motion state of vehicle for the motion tracking by video；Monitoring is single
Member, for motion state to be bound vehicle monitoring service logic, output monitoring result and instruction.
According to above-described embodiment, it is preferable that the vehicle movement recognition unit includes: tracing module, for passing through object
Tracing algorithm tracks all vehicle locations in the images to be recognized of consecutive frame；Output module, for defeated according to car tracing situation
The motion state of vehicle out.
According to above-described embodiment, it is preferable that the monitoring unit includes: first judgment module, for when vehicle is specific
When regional movement state is static, is sent to monitoring client and remind instruction.
According to above-described embodiment, it is preferable that the monitoring unit includes: the second judgment module, for working as the static of vehicle
When time is more than preset duration, is sent to monitoring client and remind instruction.
The image recorded by video monitoring end extracts video clip and carries out discriminance analysis, passes through the motion tracking of video
Information command is transferred to vehicle prison by Internet to the vehicle-state for meeting specified conditions by the motion state for identifying vehicle
Administrative center is controlled, intelligent, automatic management is carried out to associated vehicle using vehicle identification system, for using up to date technics
Means control and management urban transportation, control the operating status of each car in real time, can facilitate realization vehicle scheduling, occur in danger
When, emergency car tracking and disposition can be guided, administrative department is dredged in time, efficiently monitoring is laid a solid foundation.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (9)
1. a kind of vehicle identification and detection method based on convolutional neural networks, which comprises the following steps:
A. the picture sample for extracting one group of variety classes vehicle specific modality marks all categories vehicle in picture sample
Note；
B. marked picture sample is subjected to region segmentation and floristic analysing training using mask-rcnn；
C. communication connection is established with video monitoring end, extracts the images to be recognized of one group of random continuous in video to be identified；
D. vehicle location and type in all images to be recognized are predicted by mask-rcnn semantic segmentation；
E. the motion state of vehicle is exported by the motion tracking of video；
F. motion state is bound into vehicle monitoring service logic, output monitoring result and instruction.
2. a kind of vehicle identification and detection method based on convolutional neural networks according to claim 1, which is characterized in that institute
Stating images to be recognized is the one group of image continuously chosen in the period extracted at random in video to be identified.
3. a kind of vehicle identification and detection method based on convolutional neural networks according to claim 2, which is characterized in that step
Rapid e includes: to track all vehicle locations in the images to be recognized of consecutive frame by object tracking algorithm；According to car tracing situation
Export the motion state of vehicle.
4. according to claim 1 or a kind of 3 vehicle identifications and detection method based on convolutional neural networks, feature exist
In step f includes: when vehicle is when specific region motion state is static, to monitoring client transmission prompting instruction.
5. according to claim 1 or a kind of 3 vehicle identifications and detection method based on convolutional neural networks, feature exist
In step f includes: to send to monitoring client when the quiescent time of vehicle being more than preset duration and remind instruction.
6. a kind of vehicle identification and detection system based on convolutional neural networks characterized by comprising
Marking unit, for extracting the picture sample of one group of variety classes vehicle specific modality, by all categories in picture sample
Vehicle is marked；
Training unit, for using mask-rcnn that marked picture sample is carried out region segmentation and floristic analysing training；
Extraction unit, for establishing communication connection with video monitoring end, extract in video to be identified one group of random continuous wait know
Other image；
Information of vehicles recognition unit, for predicting vehicle location in all images to be recognized by mask-rcnn semantic segmentation
And type；
Vehicle movement recognition unit exports the motion state of vehicle for the motion tracking by video；
Monitoring unit, for motion state to be bound vehicle monitoring service logic, output monitoring result and instruction.
7. a kind of vehicle identification and detection system based on convolutional neural networks according to claim 6, which is characterized in that institute
Stating vehicle movement recognition unit includes:
Tracing module, for all vehicle locations in the images to be recognized by object tracking algorithm tracking consecutive frame；Export mould
Block, for exporting the motion state of vehicle according to car tracing situation.
8. a kind of vehicle identification and detection system based on convolutional neural networks according to claim 7, which is characterized in that institute
Stating monitoring unit includes: first judgment module, is used for when vehicle is when specific region motion state is static, to monitoring client transmission
Remind instruction.
9. a kind of vehicle identification and detection system based on convolutional neural networks according to claim 7, which is characterized in that institute
Stating monitoring unit includes: the second judgment module, for being mentioned to monitoring client transmission when the quiescent time of vehicle being more than preset duration
It wakes up and instructs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910182868.0A CN109934161B (en) | 2019-03-12 | 2019-03-12 | Vehicle identification and detection method and system based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910182868.0A CN109934161B (en) | 2019-03-12 | 2019-03-12 | Vehicle identification and detection method and system based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109934161A true CN109934161A (en) | 2019-06-25 |
| CN109934161B CN109934161B (en) | 2023-04-28 |
Family
ID=66986885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910182868.0A Active CN109934161B (en) | 2019-03-12 | 2019-03-12 | Vehicle identification and detection method and system based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109934161B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112180913A (en) * | 2020-09-01 | 2021-01-05 | 芜湖酷哇机器人产业技术研究院有限公司 | Special vehicle identification method |
| CN112686923A (en) * | 2020-12-31 | 2021-04-20 | 浙江航天恒嘉数据科技有限公司 | Target tracking method and system based on double-stage convolutional neural network |
| CN113469158A (en) * | 2021-09-06 | 2021-10-01 | 智广海联(天津)大数据技术有限公司 | Method and system for identifying illegal hazardous chemical substance transport vehicle based on convolutional neural network |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968886A (en) * | 2010-09-09 | 2011-02-09 | 西安电子科技大学 | Centroid tracking framework based particle filter and mean shift cell tracking method |
| CN103617410A (en) * | 2013-08-30 | 2014-03-05 | 重庆大学 | Highway tunnel parking detection method based on video detection technology |
| CN104070525A (en) * | 2014-06-18 | 2014-10-01 | 大连大学 | Space manipulator continuous trajectory tracking method |
| CN104282020A (en) * | 2014-09-22 | 2015-01-14 | 中海网络科技股份有限公司 | Vehicle speed detection method based on target motion track |
| CN104615142A (en) * | 2014-12-19 | 2015-05-13 | 重庆大学 | Flight controller for civil small UAV (Unmanned Aerial Vehicle) |
| CN108710875A (en) * | 2018-09-11 | 2018-10-26 | 湖南鲲鹏智汇无人机技术有限公司 | A kind of take photo by plane road vehicle method of counting and device based on deep learning |
| CN109145769A (en) * | 2018-08-01 | 2019-01-04 | 辽宁工业大学 | The target detection network design method of blending image segmentation feature |
| CN109300165A (en) * | 2018-09-14 | 2019-02-01 | 南京邮电大学 | A kind of novel target tracking localization method based on pixel characteristic |
| CN109359538A (en) * | 2018-09-14 | 2019-02-19 | 广州杰赛科技股份有限公司 | Training method, gesture identification method, device and the equipment of convolutional neural networks |
-
2019
- 2019-03-12 CN CN201910182868.0A patent/CN109934161B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968886A (en) * | 2010-09-09 | 2011-02-09 | 西安电子科技大学 | Centroid tracking framework based particle filter and mean shift cell tracking method |
| CN103617410A (en) * | 2013-08-30 | 2014-03-05 | 重庆大学 | Highway tunnel parking detection method based on video detection technology |
| CN104070525A (en) * | 2014-06-18 | 2014-10-01 | 大连大学 | Space manipulator continuous trajectory tracking method |
| CN104282020A (en) * | 2014-09-22 | 2015-01-14 | 中海网络科技股份有限公司 | Vehicle speed detection method based on target motion track |
| CN104615142A (en) * | 2014-12-19 | 2015-05-13 | 重庆大学 | Flight controller for civil small UAV (Unmanned Aerial Vehicle) |
| CN109145769A (en) * | 2018-08-01 | 2019-01-04 | 辽宁工业大学 | The target detection network design method of blending image segmentation feature |
| CN108710875A (en) * | 2018-09-11 | 2018-10-26 | 湖南鲲鹏智汇无人机技术有限公司 | A kind of take photo by plane road vehicle method of counting and device based on deep learning |
| CN109300165A (en) * | 2018-09-14 | 2019-02-01 | 南京邮电大学 | A kind of novel target tracking localization method based on pixel characteristic |
| CN109359538A (en) * | 2018-09-14 | 2019-02-19 | 广州杰赛科技股份有限公司 | Training method, gesture identification method, device and the equipment of convolutional neural networks |
Non-Patent Citations (3)
| Title |
|---|
| 付发: "基于卷积网络的遥感图像建筑物提取技术研究", 《软件工程》 * |
| 吴科君: "《基于深度学习的海面船舶目标检测》", 《全国硕士论文库》 * |
| 张礼雄: "视频中多目标车辆的检测与跟踪方法", 《计算机技术与发展》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112180913A (en) * | 2020-09-01 | 2021-01-05 | 芜湖酷哇机器人产业技术研究院有限公司 | Special vehicle identification method |
| CN112686923A (en) * | 2020-12-31 | 2021-04-20 | 浙江航天恒嘉数据科技有限公司 | Target tracking method and system based on double-stage convolutional neural network |
| CN113469158A (en) * | 2021-09-06 | 2021-10-01 | 智广海联(天津)大数据技术有限公司 | Method and system for identifying illegal hazardous chemical substance transport vehicle based on convolutional neural network |
| CN113469158B (en) * | 2021-09-06 | 2021-11-19 | 智广海联(天津)大数据技术有限公司 | Method and system for identifying illegal hazardous chemical substance transport vehicle based on convolutional neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109934161B (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110717433A (en) | Deep learning-based traffic violation analysis method and device | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN106874863A (en) | Vehicle based on depth convolutional neural networks is disobeyed and stops detection method of driving in the wrong direction | |
| CN105070053A (en) | Intelligent traffic monitoring camera for identifying vehicle illegal movement modes | |
| CN104809887B (en) | A kind of retrograde detection method of vehicle on expressway and autoalarm | |
| CN102254429A (en) | Video identification-based detection apparatus and method of vehicles against regulations | |
| CN109934161A (en) | Vehicle identification and detection method and system based on convolutional neural network | |
| CN103208190B (en) | Traffic flow detection method based on object detection | |
| CN103279756A (en) | Vehicle detecting analysis system and detecting analysis method thereof based on integrated classifier | |
| CN104282154A (en) | Vehicle overload monitoring system and method | |
| CN104809470A (en) | Vehicle converse running detection device and method based on SVM | |
| CN109410583A (en) | Traffic information collection and analysis system and operation method based on automobile data recorder | |
| CN114387785A (en) | Safety management and control method and system based on intelligent highway and storable medium | |
| CN113450573A (en) | Traffic monitoring method and traffic monitoring system based on unmanned aerial vehicle image recognition | |
| CN112669598A (en) | Intelligent traffic management system based on traffic flow | |
| CN114494998B (en) | Intelligent analysis method and system for vehicle data | |
| CN108965804A (en) | A kind of video structural technology for city security protection | |
| CN112257683A (en) | Cross-mirror tracking method for vehicle running track monitoring | |
| Ravish et al. | Intelligent traffic violation detection | |
| CN104268548A (en) | Accumulated snow detection method based on road images | |
| CN117495896A (en) | Method and system for detecting abnormal track of pedestrian in traffic environment | |
| CN115169673A (en) | Intelligent campus epidemic risk monitoring and early warning system and method | |
| Wang et al. | Vision-based highway traffic accident detection | |
| CN207938184U (en) | A kind of vehicle-mounted act of violating regulations capturing system | |
| CN117894187A (en) | Highway intellectual detection system early warning system |
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 |