CN103345840A - Video detection method of road crossing event at cross road - Google Patents
Video detection method of road crossing event at cross road Download PDFInfo
- Publication number
- CN103345840A CN103345840A CN2013102058318A CN201310205831A CN103345840A CN 103345840 A CN103345840 A CN 103345840A CN 2013102058318 A CN2013102058318 A CN 2013102058318A CN 201310205831 A CN201310205831 A CN 201310205831A CN 103345840 A CN103345840 A CN 103345840A
- Authority
- CN
- China
- Prior art keywords
- road
- video
- target
- coordinate
- crossing
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
Disclosed in the invention is a video detection method of a road crossing event at a cross road. The method is characterized in that a monitoring camera installed at a cross road collects a video signal; after the video is decoded, a computer vision and image processing technology is used to carry out road crossing event detection in a range of a certain distance nearby the cross road so as to identify targets of vehicles and pedestrians and the like on the road; a mutual conversion relation of an image pixel coordinate, a world coordinate, and a GPS coordinate is combined to obtain information of GPS positions, moving directions and speeds and the like of the targets and the obtained information is transmitted to a background control and dispatching center by a communication network. According to the method, the video collection device can be installed and maintained simply and easily; and economic and effective performances are realized. The detection method integrating with video processing, video monitoring, and real-time alarming is capable of carrying out determination and alarming on a road traffic state autonomously under the circumstances of unattended operation and tracking a moving object; and an integrated traffic management system with real-time, accurate, and efficient characteristics can be realized.
Description
Technical field
The invention belongs to digital image processing field and intelligent video monitoring technical field, be specially a kind of cross channel crossing and cross road event video detecting method.
Background technology
Intelligent transportation system realizes the advanced IT application of traffic, fully rationally utilize path resource, for traveler provides effective traffic information, disperse the traffic flow of crowded section of highway, realize motor vehicle and the optimal flow of pedestrian on road, thereby the overload of alleviating road is used, and improves conevying efficiency, sets up the road traffic running environment of safety and comfort.
Traffic target detection and information acquisition are most important in intelligent transportation system.Current, traffic detection method commonly used both at home and abroad mainly contains toroid winding detection, infrared detection and intelligent video monitoring detection.The toroid winding detection method is because of working stability, accuracy of detection is higher, use wider at present, but this method can only detect the travelling speed of motor vehicle, the line trace of going forward side by side of the magnitude of traffic flow of statistics road, the behavior that can't analyze, identify target, and also helpless to this system of detection of bicycle, in addition, toroidal installation, the maintenance cost also very big.Infrared detection is highly sensitive, and response is rapid, but infrared detector is easily affected by environment, and temperature, humidity, dust all can cause very big influence to the accuracy that detects.Detect based on the video monitoring technology based on the intelligent transportation of video, fully utilize technology such as computer vision, image processing, pattern-recognition, independently to scene analyze, information extraction and feedback.Characteristics such as it need not to destroy the road surface, suspends traffic, and has onlinely to install, debug, keep in repair, and sensing range is big, and the information extraction ability is strong, and real-time is good, thereby in traffic detection and information extraction, more and more come into one's own.Many scientific research institutions both domestic and external all handle video monitoring and study at present, and obtained very big progress, yet at present domestic also do not have a kind of cross channel crossing to cross the requirement that road event detection tracker namely satisfies universality, real-time, accuracy.
Summary of the invention
Technical purpose: the objective of the invention is to provide a kind of detection accurately, follow the tracks of timely the cross channel crossing and cross road event video detecting method.
Technical scheme: the present invention relates to a kind of cross channel crossing and cross road event video detecting method, comprise the steps:
The video monitoring video camera that utilizes the cross channel crossing to arrange is gathered the traffic video picture of intersection in real time, and with video signal transmission to processing unit;
The decoding video signal of processing unit to collecting;
Adopt computer vision and image processing techniques, detect carry out foreground target through decoded frame of video, identify automobile or pedestrian, and target is followed the tracks of;
According to foreground target information the target on the road is judged, if cross the road event, provided security warning;
The target information data that current highway section name data, extraction moment data and extraction obtain are controlled and the dispatching center to the rear by network delivery, made corresponding decision by the dispatching center.
It is characterized in that: in decoding rear video signal, inserting the road basic parameter that process is imported or calculated, and signal is preserved.
Described road parameters comprises transformational relation between image pixel coordinate, world coordinates and the gps coordinate three and the boundary information of road area-of-interest, and the transformational relation between described image pixel coordinate, world coordinates and the gps coordinate three is as follows:
The view plane coordinate (x, y) be converted to world coordinates (X, Y):
A wherein, b, c are parameter, W
RoadBe road width, W
ImageFor road width at this some pixel number of being expert at and occupying of frame of video.
Ground coordinate is to the conversion of gps coordinate: set known point A and known point B, the path coordinate (x that known A is ordered
A, y
A), the path coordinate (x that B is ordered
B, y
B), and the gps coordinate value at A place is (la
A, lo
A), desire to ask the gps coordinate value (la represents latitude, and lo represents longitude, down with) at B place, the B gps coordinate value of ordering then, for
GPS
B＝(la
B,lo
B)＝(la
C,lo
B)
Carrying out at first video being carried out automatic background extraction, adaptive background renewal and the anti-shake processing of video camera before foreground target detects, the method for recycling moving object detection extracts foreground target.
The method of moving object detection comprises the steps:
After present frame and background frames done difference, carry out threshold value and cut apart binaryzation;
The difference frame is done shadow removal;
Through some morphologic processing, obtain more complete foreground pixel block;
Adopt the connection labeling algorithm that these blocks are carried out mark, location;
According to clarification of objective it is carried out Classification and Identification.
Morphology is handled and to be comprised with erosion algorithm and remove isolated noise, refinement edge and fill the cavity of target area with expansion algorithm, specifically, represent processed bianry image sample with A, B represents the structural element selected in the processing procedure, the symbolic representation erosion operation, formula is expressed as follows:
AB={p ∈ ε
2: p+b ∈ A, for each b ∈ B}
ε in the formula
2Represent two-dimentional theorem in Euclid space.
Dilation operation is the union that has among the relative structural element B of image A after the b translation, comes mark with ⊕:
A ⊕ B={p ∈ ε
2: p=x+b, x ∈ X and b ∈ B}.
Decision process in the step 4 comprises the steps:
From detected pedestrian's target, extract information such as GPS position, direction of motion, travelling speed;
According to pedestrian's objective attribute target attribute and movable information, judge to have or not and cross the generation of road event;
Cross the road event as existence, then further judging has pedestrian's target whether vehicle target is arranged on every side;
If exist vehicle target then to start autoalarm, provide information warning.
Data described in the step 5 at first through being encapsulated into network frame, transfer to traffic control and dispatching center by wired or wireless network then.
Beneficial effect: the present invention compared with prior art need not manual intervention after system's operate as normal, anti-noise ability is strong, reliable operation; Network is transmission process useful information afterwards only, has saved bandwidth, has alleviated the processing pressure of rear control center computing machine simultaneously again; Send control dispatching center, rear to by existing information wireless or that cable network obtains processing, need not to lay in addition transmission line, convenient feasible.
Description of drawings
Fig. 1 is main composition module frame chart of the present invention;
Fig. 2 is main algorithm process flow diagram of the present invention.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, be described in further detail below in conjunction with the enforcement of accompanying drawing to technical scheme:
Fig. 1 is main composition module frame chart of the present invention.Gather the road video information in real time by the monitoring camera equipment that is erected at the cross channel crossing, after the decoding of video decode module, video flowing is imported core processing module handle; Core processing module is mainly finished the extraction of road target detection, identification and tracking and target GPS position, direction of motion, travelling speed information, finishes the detection and the security information hint instructions that cross the road event and sends; Before detecting beginning, need to calculate or read the road essential information, as sensing range, transformational relation between image pixel coordinate, world coordinates and the gps coordinate three etc., these essential informations leave in the storer after calculating for the first time, can directly from storer, read road information if system restarts, need not to calculate again; Cross the generation of road event if detected, then alarm provides the security information caution, with the information of extracting, transfer to the traffic control dispatching center as information such as road name, detection time, target GPS position, travelling speed, direction of motion by wired or wireless network simultaneously.
Figure is main process flow diagram of the present invention.Mainly comprise following step:
System initialization.Finish the initialization of equipment and major parameter, make it to be in normal operating conditions;
Calculate or read the road essential information.If for the first time road is detected, need utilize Man Machine Interface to carry out surveyed area and determine.What detect usually is the stretch face of intersection certain limit distance, as the road of distance video camera 10-120 rice scope, the cross channel crossing is within the detected scope.Finish conversion from the pixel coordinate to the world coordinates according to the video camera imaging principle.Base area geometry of sphere relation, get the gps coordinate of a reference point at road after, calculate the gps coordinate of road arbitrfary point, finish the mutual conversion between pixel coordinate, world coordinates, the gps coordinate three, and the transformational relation of zone boundary information and three kinds of coordinates is kept in storer or the file.If not detect for the first time, can directly from storer or file, read data, be used for follow-up computing;
Described road parameters comprises transformational relation between image pixel coordinate, world coordinates and the gps coordinate three and the boundary information of road area-of-interest, and the transformational relation between described image pixel coordinate, world coordinates and the gps coordinate three is as follows:
The view plane coordinate (x, y) be converted to world coordinates (X, Y):
A wherein, b, c are parameter, W
RoadBe road width, W
ImageFor road width at this some pixel number of being expert at and occupying of frame of video.
Ground coordinate is to the conversion of gps coordinate: set known point A and known point B, the path coordinate (x that known A is ordered
A, y
A), the path coordinate (x that B is ordered
B, y
B), and the gps coordinate value at A place is (la
A, lo
A), desire to ask the gps coordinate value (la represents latitude, and lo represents longitude, down with) at B place, the B gps coordinate value of ordering then, for
GPS
B＝(la
B,lo
B)＝(la
C,lo
B)
3) to cross channel crossing target detection, identification and tracking.In the surveyed area scope of delimiting, target is detected, at first carry out the automatic extraction of background, shake is handled to camera, image to the camera input carries out the filtering processing, method according to moving object detection extracts foreground target then, according to coordinate transformation relation, obtains the position at target place, use target tracking algorism that target is followed the tracks of, judge objective attribute target attribute according to target signature information; Carrying out at first video being carried out automatic background extraction, adaptive background renewal and the anti-shake processing of video camera before foreground target detects, the method for recycling moving object detection extracts foreground target.
The method of moving object detection comprises the steps:
After present frame and background frames done difference, carry out threshold value and cut apart binaryzation;
The difference frame is done shadow removal;
Through some morphologic processing, obtain more complete foreground pixel block;
Adopt the connection labeling algorithm that these blocks are carried out mark, location;
According to clarification of objective it is carried out Classification and Identification.
4) further judge to have or not according to information obtained in the step 3 and cross the road event and take place, mainly judge and have or not pedestrian's existence and travel direction thereof, speed in the crossing, judge simultaneously and have or not direction of vehicle movement towards the pedestrian position on the road surface, judge hazard level, provide safety instruction information;
Decision process in the step 4 comprises the steps:
From detected pedestrian's target, extract information such as GPS position, direction of motion, travelling speed;
According to pedestrian's objective attribute target attribute and movable information, judge to have or not and cross the generation of road event;
Cross the road event as existence, then further judging has pedestrian's target whether vehicle target is arranged on every side;
If exist vehicle target then to start autoalarm, provide information warning.
5) information envelopes such as the road name that will obtain by above-mentioned steps, detection time, target GPS position, movement velocity, traffic direction change into Frame, transfer to the traffic control dispatching center by existing wired or wireless network.
Core processing module of the present invention can realize at hardware chip, as employing field programmable gate array (FPGA), digital signal processing chip (DSP) etc., but is not limited only to this.
Provide the example of a concrete practice below:
The monitoring camera equipment frame is located at high about 6 meters position, cross channel crossing, gathers the road video information in real time, after the decoding of video decode module, video flowing is imported core processing module handle; Core processing module is mainly finished the extraction of road target detection, identification and tracking and target GPS position, direction of motion, travelling speed information, finishes the detection and the security information hint instructions that cross the road event and sends.
At first carry out system initialization.Finish the initialization of equipment and major parameter, make it to be in normal operating conditions.Calculate or read the road essential information then.For the first time road is detected, need utilize Man Machine Interface to carry out surveyed area and determine.What detect is the stretch face of intersection certain limit distance, apart from the road of video camera 10-120 rice scope, the cross channel crossing is within the detected scope.Finish conversion from the pixel coordinate to the world coordinates according to the video camera imaging principle.Base area geometry of sphere relation, get the gps coordinate of a reference point at road after, calculate the gps coordinate of road arbitrfary point, finish the mutual conversion between pixel coordinate, world coordinates, the gps coordinate three, and the transformational relation of zone boundary information and three kinds of coordinates is kept in storer or the file.If not detect for the first time, can directly from storer or file, read data, be used for follow-up computing.
Cross channel crossing target detection, identification and tracking.In the surveyed area scope of delimiting, target is detected, at first carry out the automatic extraction of background, shake is handled to camera, image to the camera input carries out the filtering processing, method according to moving object detection extracts foreground target then, according to coordinate transformation relation, obtains the position at target place, use target tracking algorism that target is followed the tracks of, judge objective attribute target attribute according to target signature information.
Further judge to have or not according to the information of extracting and cross the road event and take place, mainly judge and have or not pedestrian's existence and travel direction thereof, speed in the crossing, judge simultaneously to have or not direction of vehicle movement towards the pedestrian position on the road surface, judge hazard level, provide safety instruction information.Information envelopes such as the road name that will obtain by above-mentioned steps, detection time, target GPS position, movement velocity, traffic direction change into Frame, transfer to the traffic control dispatching center by existing wired or wireless network.
Claims (8)
1. road event video detecting method is crossed at a cross channel crossing, it is characterized in that: comprise the steps:
1) the video monitoring video camera that utilizes the cross channel crossing to arrange is gathered the traffic video picture of intersection in real time, and with video signal transmission to processing unit;
2) decoding video signal of processing unit to collecting;
3) adopt computer vision and image processing techniques, detect carry out foreground target through decoded frame of video, identify automobile or pedestrian, and target is followed the tracks of;
4) according to foreground target information the target on the road is judged, if cross the road event, provided security warning;
5) the target information data that current highway section name data, extraction moment data and extraction are obtained to rear control and dispatching center, are made corresponding decision by the dispatching center by network delivery.
2. road event video detecting method is crossed at a kind of cross channel according to claim 1 crossing, it is characterized in that: inserting in decoding rear video signal through input or the road basic parameter that calculates, and signal is preserved.
3. road event video detecting method is crossed at a kind of cross channel according to claim 2 crossing, it is characterized in that: described road parameters comprises transformational relation between image pixel coordinate, world coordinates and the gps coordinate three and the boundary information of road area-of-interest, and the transformational relation between described image pixel coordinate, world coordinates and the gps coordinate three is as follows:
1) the view plane coordinate (x, y) be converted to world coordinates (X, Y):
A wherein, b, c are parameter, W
RoadBe road width, W
ImageFor road width at this some pixel number of being expert at and occupying of frame of video.
2) ground coordinate is to the conversion of gps coordinate: set known point A and known point B, the path coordinate (x that known A is ordered
A, y
A), the path coordinate (x that B is ordered
B, y
B), and the gps coordinate value at A place is (la
A, lo
A), desire to ask the gps coordinate value (la represents latitude, and lo represents longitude, down with) at B place, the B gps coordinate value of ordering then, for
GPS
B＝(la
B,lo
B)＝(la
C,lo
B)
4. road event video detecting method is crossed at a kind of cross channel according to claim 1 crossing, it is characterized in that: carrying out at first video being carried out automatic background extraction, adaptive background renewal and the anti-shake processing of video camera before foreground target detects, the method for recycling moving object detection extracts foreground target.
5. road event video detecting method is crossed at a kind of cross channel according to claim 4 crossing, and it is characterized in that: the method for moving object detection comprises the steps:
1) present frame and background frames are done difference after, carry out threshold value and cut apart binaryzation;
2) the difference frame is done shadow removal;
3) through some morphologic processing, obtain more complete foreground pixel block;
4) adopt the connection labeling algorithm that these blocks are carried out mark, location;
5) according to clarification of objective it is carried out Classification and Identification.
6. road event video detecting method is crossed at a kind of cross channel according to claim 5 crossing, it is characterized in that: morphology is handled and to be comprised with erosion algorithm and remove isolated noise, refinement edge and fill the cavity of target area with expansion algorithm, specifically, represent processed bianry image sample with A, B represents the structural element selected in the processing procedure, the symbolic representation erosion operation, formula is expressed as follows:
AB={p ∈ ε
2: p+b ∈ A, for each b ∈ B}
ε in the formula
2Represent two-dimentional theorem in Euclid space.
Dilation operation is the union that has among the relative structural element B of image A after the b translation, comes mark with ⊕:
A ⊕ B={p ∈ ε
2: p=x+b, x ∈ X and b ∈ B}.
7. road event video detecting method is crossed at a kind of cross channel according to claim 1 crossing, and it is characterized in that: the decision process in the step 4 comprises the steps:
1) from detected pedestrian's target, extracts information such as GPS position, direction of motion, travelling speed;
2) according to pedestrian's objective attribute target attribute and movable information, judge to have or not and cross the generation of road event;
3) cross the road event as existence, then further judging has pedestrian's target whether vehicle target is arranged on every side;
4) if exist vehicle target then to start autoalarm, provide information warning.
8. road event video detecting method is crossed at a kind of cross channel according to claim 1 crossing, it is characterized in that: the data described in the step 5 at first through being encapsulated into network frame, transfer to traffic control and dispatching center by wired or wireless network then.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310205831.8A CN103345840B (en) | 2013-05-28 | 2013-05-28 | Road incidents video detecting method is crossed at a kind of cross channel crossing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310205831.8A CN103345840B (en) | 2013-05-28 | 2013-05-28 | Road incidents video detecting method is crossed at a kind of cross channel crossing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103345840A true CN103345840A (en) | 2013-10-09 |
| CN103345840B CN103345840B (en) | 2015-09-23 |
Family
ID=49280631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310205831.8A Expired - Fee Related CN103345840B (en) | 2013-05-28 | 2013-05-28 | Road incidents video detecting method is crossed at a kind of cross channel crossing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103345840B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104916132A (en) * | 2015-05-14 | 2015-09-16 | 扬州大学 | Method used for determining traffic flow running track of intersection |
| CN105025099A (en) * | 2015-07-15 | 2015-11-04 | 同济大学 | Smart camera network system and camera network dynamic task allocation method |
| CN106373430A (en) * | 2016-08-26 | 2017-02-01 | 华南理工大学 | Intersection pass early warning method based on computer vision |
| CN107507298A (en) * | 2017-08-11 | 2017-12-22 | 南京阿尔特交通科技有限公司 | A kind of multimachine digital video vehicle operation data acquisition method and device |
| CN108040221A (en) * | 2017-11-30 | 2018-05-15 | 江西洪都航空工业集团有限责任公司 | A kind of intelligent video analysis and monitoring system |
| CN108062861A (en) * | 2017-12-29 | 2018-05-22 | 潘彦伶 | A kind of intelligent traffic monitoring system |
| CN108322699A (en) * | 2018-01-23 | 2018-07-24 | 东南大学 | A method of based on video images detection arc-flash |
| CN109615866A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | Traffic monitoring system Internet-based |
| CN110688903A (en) * | 2019-08-30 | 2020-01-14 | 陕西九域通创轨道系统技术有限责任公司 | Obstacle extraction method based on camera data of train AEB system |
| TWI704529B (en) * | 2015-12-11 | 2020-09-11 | 瑞典商安訊士有限公司 | Method and device for detecting an object crossing event at a predetermined first line in a scene |
| CN112349096A (en) * | 2020-10-28 | 2021-02-09 | 厦门博海中天信息科技有限公司 | Method, system, medium and equipment for intelligently identifying pedestrians on road |
| CN112435475A (en) * | 2020-11-23 | 2021-03-02 | 北京软通智慧城市科技有限公司 | Traffic state detection method, device, equipment and storage medium |
| CN113022447A (en) * | 2019-12-24 | 2021-06-25 | 宏碁股份有限公司 | Warning method and warning system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2442049A (en) * | 2006-07-26 | 2008-03-26 | Joseph Farrell-Dillon | Proximity sensor activated camera |
| CN101308606A (en) * | 2007-05-18 | 2008-11-19 | 刘涛 | Traffic information collecting apparatus and method thereof |
| CN101777263A (en) * | 2010-02-08 | 2010-07-14 | 长安大学 | Traffic vehicle flow detection method based on video |
| CN101964145A (en) * | 2009-07-23 | 2011-02-02 | 北京中星微电子有限公司 | Automatic license plate recognition method and system |
| WO2012029382A1 (en) * | 2010-08-31 | 2012-03-08 | 本田技研工業株式会社 | Vehicle surroundings monitoring device |
-
2013
- 2013-05-28 CN CN201310205831.8A patent/CN103345840B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2442049A (en) * | 2006-07-26 | 2008-03-26 | Joseph Farrell-Dillon | Proximity sensor activated camera |
| CN101308606A (en) * | 2007-05-18 | 2008-11-19 | 刘涛 | Traffic information collecting apparatus and method thereof |
| CN101964145A (en) * | 2009-07-23 | 2011-02-02 | 北京中星微电子有限公司 | Automatic license plate recognition method and system |
| CN101777263A (en) * | 2010-02-08 | 2010-07-14 | 长安大学 | Traffic vehicle flow detection method based on video |
| WO2012029382A1 (en) * | 2010-08-31 | 2012-03-08 | 本田技研工業株式会社 | Vehicle surroundings monitoring device |
Non-Patent Citations (4)
| Title |
|---|
| BING-FEI WU ET AL.: "A New Approach to Video-Based Traffic Surveillance Using Fuzzy Hybrid Information Inference Mechanism", 《IEEE INTELLIGENT TRANSPORTATION SYSTEMS SOCIETY 》 * |
| 杨大鹏: "道路行人特征视觉检测方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 樊兆宾: "交通检测与超速抓拍一体化系统设计", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 黄德宝: "智能交通监控系统中运动目标的检测与预警技术", 《中国学位论文全文数据库》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104916132A (en) * | 2015-05-14 | 2015-09-16 | 扬州大学 | Method used for determining traffic flow running track of intersection |
| CN105025099A (en) * | 2015-07-15 | 2015-11-04 | 同济大学 | Smart camera network system and camera network dynamic task allocation method |
| TWI704529B (en) * | 2015-12-11 | 2020-09-11 | 瑞典商安訊士有限公司 | Method and device for detecting an object crossing event at a predetermined first line in a scene |
| CN106373430A (en) * | 2016-08-26 | 2017-02-01 | 华南理工大学 | Intersection pass early warning method based on computer vision |
| CN106373430B (en) * | 2016-08-26 | 2023-03-31 | 华南理工大学 | Intersection traffic early warning method based on computer vision |
| CN107507298B (en) * | 2017-08-11 | 2019-10-22 | 南京阿尔特交通科技有限公司 | A kind of multimachine digital video vehicle operation data acquisition method and device |
| CN107507298A (en) * | 2017-08-11 | 2017-12-22 | 南京阿尔特交通科技有限公司 | A kind of multimachine digital video vehicle operation data acquisition method and device |
| CN108040221B (en) * | 2017-11-30 | 2020-05-12 | 江西洪都航空工业集团有限责任公司 | Intelligent video analysis and monitoring system |
| CN108040221A (en) * | 2017-11-30 | 2018-05-15 | 江西洪都航空工业集团有限责任公司 | A kind of intelligent video analysis and monitoring system |
| CN108062861A (en) * | 2017-12-29 | 2018-05-22 | 潘彦伶 | A kind of intelligent traffic monitoring system |
| CN108062861B (en) * | 2017-12-29 | 2021-01-15 | 北京安自达科技有限公司 | Intelligent traffic monitoring system |
| CN108322699A (en) * | 2018-01-23 | 2018-07-24 | 东南大学 | A method of based on video images detection arc-flash |
| CN108322699B (en) * | 2018-01-23 | 2020-02-18 | 东南大学 | Method for detecting arc flash based on video image |
| CN109615866A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | Traffic monitoring system Internet-based |
| CN110688903A (en) * | 2019-08-30 | 2020-01-14 | 陕西九域通创轨道系统技术有限责任公司 | Obstacle extraction method based on camera data of train AEB system |
| CN110688903B (en) * | 2019-08-30 | 2023-09-26 | 湖南九域同创高分子新材料有限责任公司 | Barrier extraction method based on train AEB system camera data |
| CN113022447A (en) * | 2019-12-24 | 2021-06-25 | 宏碁股份有限公司 | Warning method and warning system |
| CN112349096A (en) * | 2020-10-28 | 2021-02-09 | 厦门博海中天信息科技有限公司 | Method, system, medium and equipment for intelligently identifying pedestrians on road |
| CN112435475A (en) * | 2020-11-23 | 2021-03-02 | 北京软通智慧城市科技有限公司 | Traffic state detection method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103345840B (en) | 2015-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103345840A (en) | Video detection method of road crossing event at cross road | |
| CN102779280B (en) | Traffic information extraction method based on laser sensor | |
| CN103279949B (en) | Based on the multi-camera parameter automatic calibration system operation method of self-align robot | |
| CN104008645B (en) | One is applicable to the prediction of urban road lane line and method for early warning | |
| CN101458871B (en) | Intelligent traffic analysis system and application system thereof | |
| CN107380163A (en) | Automobile intelligent alarm forecasting system and its method based on magnetic navigation | |
| CN105513371B (en) | A kind of highway parking offense detection method based on Density Estimator | |
| CN102147971A (en) | Traffic information acquisition system based on video image processing technology | |
| EP2813973B1 (en) | Method and system for processing video image | |
| CN103903465A (en) | Method and system for releasing reason for road congestion in real time | |
| CN103208184A (en) | Traffic incident video detection method for highway | |
| CN103310206B (en) | A kind of vehicle using motor detection method based on many features and multiframe information fusion | |
| CN113313914B (en) | Group fog monitoring method, device and system and storage medium | |
| CN202422420U (en) | Illegal parking detection system based on video monitoring | |
| CN114387785A (en) | Safety management and control method and system based on intelligent highway and storable medium | |
| CN103149603A (en) | Road weather detection method based on video | |
| CN104867331B (en) | Traffic incidents detection method and device based on microwave | |
| CN106960193A (en) | A kind of lane detection apparatus and method | |
| Abdelhalim et al. | A framework for real-time traffic trajectory tracking, speed estimation, and driver behavior calibration at urban intersections using virtual traffic lanes | |
| CN104463913A (en) | Intelligent illegal parking detection device and method | |
| CN204557788U (en) | Based on the traffic incidents detection device of microwave | |
| CN204178551U (en) | There is the traffic incidents detection device of video acquisition function | |
| CN114333331B (en) | Method and system for identifying vehicle passing information and vehicle weight of multi-lane bridge | |
| CN116311113A (en) | Driving environment sensing method based on vehicle-mounted monocular camera | |
| Liu et al. | Real-Time Multi-Task Environmental Perception System for Traffic Safety Empowered by Edge Artificial Intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150923 Termination date: 20210528 |