CN114140719A - AI traffic video analysis technology - Google Patents
AI traffic video analysis technology Download PDFInfo
- Publication number
- CN114140719A CN114140719A CN202111437012.7A CN202111437012A CN114140719A CN 114140719 A CN114140719 A CN 114140719A CN 202111437012 A CN202111437012 A CN 202111437012A CN 114140719 A CN114140719 A CN 114140719A
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- video
- traffic
- target
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an AI traffic video analysis technology, comprising a hardware part and a software part; the intelligent traffic anomaly detection and alarm system comprises a hardware part and a software part, wherein the hardware part comprises an edge calculation box, the software part comprises an edge calculation equipment management platform, a video AI analysis system and a data management platform, and the edge calculation equipment management platform is provided with a video structuring system, a vehicle identification system, an event identification system and a video concentration system.
Description
Technical Field
The invention relates to the technical field of frequent AI analysis, in particular to an AI traffic video analysis technology.
Background
The video analysis technology is introduced into the traffic field of China at the beginning of the century, and video event detection is popularized and applied in a wide range of national highway video monitoring systems due to the advantages of convenience in application, wide visual field range, large information amount, what you see is what you get and the like. The system is an automatic detection and alarm system for common traffic abnormal events such as abnormal parking, retrograde motion, low-speed traffic, congestion queuing, sprinkles, pedestrians and the like in the road traffic running process based on real-time analysis of monitoring video streams and by adopting core algorithms such as deep target detection, motion detection, model detection, track tracking, behavior analysis and the like. The intelligent visual monitoring system is linked with an expressway road monitoring system to realize alarm, so that workers can be relieved from monotonous and repeated human eye video monitoring, in recent years, technologies such as big data, artificial intelligence and the like are gradually deepened into the field of intelligent transportation, and video detection is taken as a sensor technology with large information amount, strong real-time performance and good traceability and is still the most direct and effective information acquisition means in the future; how to solve the problems faced by video detection systems using new technologies has become an important research topic!
The traditional video event detection system has the outstanding problems of high false alarm rate, delayed alarm, difficult query and the like.
Disclosure of Invention
Aiming at the technical problems, the invention provides an AI traffic video analysis technology to solve the problems in the prior art.
In order to achieve the purpose, the invention adopts the technical scheme that:
the invention provides an AI traffic video analysis technology, which is characterized in that: comprises a hardware part and a software part; the system comprises a hardware part and a software part, wherein the hardware part comprises front-end monitoring equipment, a processor and a monitoring application platform, the software part comprises a video structuring system, a vehicle identification system, an event identification system, a video concentration system and a traffic parameter system, the video structuring system comprises a first target detection module, a target identification module and a target tracking module, the vehicle identification system comprises a vehicle identification module, a vehicle brand identification module, a vehicle type identification module and a pedestrian and non-motor vehicle identification module, the event identification system comprises an abnormal parking identification module, a vehicle reverse driving identification module and a pedestrian crossing identification module, and the video concentration system comprises a second target detection module, a track tracking module, a track optimization module and a video compression module.
By adopting the technical scheme, the invention
Preferably, the processor is an AI processor.
By adopting the technical scheme, the video stream is input into the AI main control computer at the front end through the wired network for algorithm processing, data including traffic events, traffic parameters, vehicle structuralization, video concentration results and the like are obtained, and the data are uploaded to the monitoring application platform in real time.
Preferably, a data connection is established between the front-end monitoring device and the processor, and the processor and the monitoring application platform are in data connection.
Preferably, the first target detection module adopts a target detection algorithm and is used for automatically detecting and positioning targets such as vehicles, non-motor vehicles, pedestrians and the like in the image;
the target identification module adopts a target identification algorithm and is used for automatically detecting and identifying the attributes of the targets such as vehicles, non-motor vehicles, pedestrians and the like in the image;
the target tracking module adopts a target tracking algorithm and is used for establishing a tracking track for detected targets such as motor vehicles, non-motor vehicles, pedestrians and the like and continuously tracking and analyzing the targets;
preferably, the vehicle identification module adopts a vehicle license plate identification algorithm and is used for identifying a license plate number, a license plate color and a license plate structure;
the vehicle brand identification module adopts a vehicle brand identification algorithm and is used for identifying the brand of the vehicle;
the vehicle type identification module adopts a vehicle type identification algorithm and is used for identifying vehicle types such as passenger cars, vans, trucks, passenger cars, motorcycles and the like;
the pedestrian and non-motor vehicle identification module is used for identifying and providing the identification capability of non-motor vehicles such as electric vehicles, bicycles, tricycles and pedestrians.
Preferably, the abnormal parking module adopts an abnormal parking detection algorithm and is used for setting thresholds such as abnormal parking response time, vehicle speed and the like, so that the abnormal parking detection requirements in different areas such as a traffic lane, an emergency lane and the like can be met;
the vehicle reverse running adopts a vehicle reverse running detection algorithm, is used for setting threshold values such as vehicle reverse running response time, vehicle speed and the like, and can meet the vehicle reverse running detection requirements in different areas such as a running lane, an emergency lane and the like;
the pedestrian crossing adopts a pedestrian crossing detection algorithm, is used for setting thresholds such as response time, walking speed, sensitivity and the like of a pedestrian crossing event, and can meet the pedestrian crossing detection requirements in different areas such as a traffic lane, an emergency lane and the like;
preferably, the traffic flow module adopts a video coil-imitating algorithm and is used for automatically detecting and counting the traffic section and the lane flow of the road;
the speed detection module adopts a video coil-imitating algorithm and is used for monitoring and statistically analyzing the speed of the vehicle passing through a section and a lane in real time;
the average time occupancy module is used for calculating the percentage of the time of the vehicle on the corresponding lane or section in the statistical time period to the time of the vehicle not on the corresponding lane or section;
and the space occupancy module is used for counting the percentage of the occupied space of the lane or the section vehicle and the space without the vehicle in the time period.
Preferably, the second target detection module adopts algorithms such as motion detection, a background model, a scene model and the like, and is used for automatically detecting and extracting a motion target and other interested targets in an original image;
the trajectory tracking module adopts a trajectory tracking algorithm and is used for establishing tracking trajectory data for the extracted target based on space-time logic, target operation characteristics and the like;
the track optimization module optimizes the running track of the concerned target by adopting a track optimization algorithm and is used for filtering factors such as environmental interference, invalid targets and the like;
the video compression module adopts a video coding compression algorithm and is used for compressing the main target information and the effective image and generating a quick retrieval index picture so as to realize effective concentration processing on the original video.
Preferably, the monitoring application center comprises a GIS visual display module, an event visual module, a man-vehicle intelligent query module, a video retrieval module and a flow data visual module, and is used for providing business entries for industrial customers based on applications such as video event and flow perception, video structuring and video concentration.
Preferably, the platform application subsystem comprises a data access server, a database server, a WEB application server, an application client and an application end monitoring large screen, the data access server realizes the collection and forwarding of front-end alarm event data, video recording and traffic parameter data, the database server realizes the storage and query support of traffic events, traffic parameter data and other data, and the WEB application server is used for deploying an application platform server program and providing support for the access of the application client data and the like.
The technical scheme has the following advantages or beneficial effects:
1. the intelligent traffic abnormal event detection and identification system can intelligently detect and identify traffic abnormal events in various scenes such as expressways, national and provincial road mainlines, urban roads and the like based on technologies such as deep learning, track tracking and the like, can automatically detect and alarm conventional events such as abnormal parking, vehicle retrograde motion, pedestrian crossing and the like, and can record high-definition video recording of the events.
2. The method is characterized in that a depth target recognition technology is adopted to concentrate and extract important targets, tracks, behaviors, scenes and the like in the video and store the extracted important targets, tracks, behaviors, scenes and the like into video segments, and the concentrated video results can be quickly retrieved, called, played and the like at a monitoring application platform end through indexing dimensions such as pictures, time, positions, scene results and the like.
3. The images or videos of the vehicles or pedestrians in the corresponding time periods can be screened out through various characteristics of the vehicles or pedestrians by the monitoring application platform, and the images can be searched according to the selected images.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
The appearances of the terms first, second, and third, if any, are used for descriptive purposes only and are not intended to be limiting or imply relative importance.
Unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are intended to be inclusive and mean, for example, that they may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Technical solutions in the embodiments of the present invention are described, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. Thus, the detailed description of the embodiments of the present invention provided below is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the invention without making creative efforts, belong to the protection scope of the invention.
An AI traffic video analysis technique comprises a hardware part and a software part; the hardware part comprises a front-end monitoring device 1, a processor 2 and a monitoring application platform 3, the software part comprises a video structuring system 4, a vehicle identification system 5, an event identification system 6, a video concentrating system 7 and a traffic parameter system 8, the video structuring system 4 comprises a first target detection module 41, a target identification module 42 and a target tracking module 43, the vehicle identification system 5 comprises a vehicle identification module 51, a vehicle brand identification module 52, a vehicle type identification module 53 and a pedestrian and non-motorized vehicle identification module 54, the event identification system 6 comprises an abnormal parking identification module 61, a vehicle reverse driving identification module 62 and a pedestrian crossing identification module 63, and the video concentrating system 7 comprises a second target detection module 71, a track tracking module 72, a track optimization module 73 and a video compression module 74.
The processor 2 is an AI processor 2.
The data connection is established between the front-end monitoring equipment 1 and the processor 2, and the processor 2 and the monitoring application platform 3 are in data connection.
The first target detection module 41 adopts a target detection algorithm and is used for automatically detecting and positioning targets such as vehicles, non-motor vehicles, pedestrians and the like in the image;
the target identification module 42 adopts a target identification algorithm and is used for automatically detecting and identifying the attributes of the targets such as vehicles, non-motor vehicles, pedestrians and the like in the image;
the target tracking module 43 adopts a target tracking algorithm and is used for establishing a tracking track for detected targets such as motor vehicles, non-motor vehicles, pedestrians and the like, and continuously tracking and analyzing the targets;
the license plate recognition module adopts a vehicle license plate recognition algorithm and is used for recognizing license plate numbers, license plate colors and license plate structures;
the vehicle recognition module 51 adopts a vehicle license plate recognition algorithm and is used for recognizing license plate numbers, license plate colors and license plate structures;
the vehicle brand identification module 52 employs a vehicle brand identification algorithm for identifying a vehicle brand;
the vehicle type identification module 53 adopts a vehicle type identification algorithm and is used for identifying vehicle types such as passenger cars, vans, trucks, passenger cars, motorcycles and the like;
the pedestrian and non-motor vehicle identification module 54 is used to identify and provide identification capability for non-motor vehicles such as electric vehicles, bicycles, tricycles and pedestrians.
The abnormal parking module adopts an abnormal parking detection algorithm and is used for setting thresholds such as abnormal parking response time, vehicle speed and the like, so that the abnormal parking detection requirements in different areas such as a traffic lane, an emergency lane and the like can be met;
the vehicle reverse running adopts a vehicle reverse running detection algorithm, is used for setting threshold values such as vehicle reverse running response time, vehicle speed and the like, and can meet the vehicle reverse running detection requirements in different areas such as a running lane, an emergency lane and the like;
the pedestrian crossing adopts a pedestrian crossing detection algorithm, is used for setting thresholds such as response time, walking speed, sensitivity and the like of a pedestrian crossing event, and can meet the pedestrian crossing detection requirements in different areas such as a traffic lane, an emergency lane and the like;
the traffic flow module 81 adopts a video coil-imitating algorithm and is used for automatically detecting and counting the traffic section and the lane flow of the road;
the speed detection 82 module adopts a video coil-tracing algorithm and is used for monitoring and statistically analyzing the speed of the vehicle passing through a section and a lane in real time;
the average time occupancy module 83 is configured to calculate the percentage of the time when the vehicle is present in the corresponding lane or section within the statistical time period;
the space occupancy module 84 is configured to count the percentage of the occupied space of the lane or the section vehicle and the occupied space of the empty vehicle in the time period.
The second target detection module 71 adopts algorithms such as motion detection, a background model, a scene model and the like, and is used for automatically detecting and extracting a motion target and other interested targets in an original image;
the trajectory tracking module 72 adopts a trajectory tracking algorithm and is used for establishing tracking trajectory data for the extracted target based on space-time logic, target running characteristics and the like;
the trajectory optimization module 73 optimizes the operation trajectory of the concerned target by adopting a trajectory optimization algorithm, and is used for filtering factors such as environmental interference and invalid targets;
the video compression module 74 employs a video coding compression algorithm, and is configured to compress the main target information and the effective image and generate a fast search index picture, so as to implement effective concentration processing on the original video.
The monitoring application center comprises a platform application subsystem 31, a GIS visual display module 32, an event visual module 33, a man-vehicle intelligent query module 34, a video retrieval module 35 and a flow data visual module 36, and is used for providing business entries for industrial customers based on applications such as video event and flow sensing, video structuring and video concentration.
The platform application subsystem 31 comprises a data access server 311, a database server 312, a WEB application server 313, an application client 314 and an application monitoring large screen 315, the data access server 311 realizes the collection and forwarding of front-end alarm event data, video recording and traffic parameter data, the database server 312 realizes the storage and query support of traffic events, traffic parameter data and other data, and the WEB application server 313 is used for deploying application platform server programs and providing support for data access and the like of the application client 314.
Example 1: the specific implementation of the human-vehicle intelligent query module 34 of the AI traffic video analysis technology provided by the invention is as follows:
the front-end monitoring equipment 1 classifies monitoring pictures or captured abnormal behavior pictures and transmits the monitoring pictures or the captured abnormal behavior pictures to the database server 312, when information inquiry is needed through vehicle information, a vehicle brand is selected through an application server, a sub-brand is selected, a vehicle type is selected, a toll vehicle type is selected, vehicle usage is selected, vehicle body color is selected, equipment direction is selected, license plate color is selected, license plate number is designated, an access point position is selected, a viewing time period is selected, after the inquiry is completed, videos and pictures meeting conditions can be called out through set adjustment through the processor 2, and accurate inquiry is achieved.
Example 2: the specific implementation of the human-vehicle intelligent query module 34 of the AI traffic video analysis technology provided by the invention is as follows: the front-end monitoring equipment 1 classifies a monitoring picture or a snap-shot abnormal behavior picture and transmits the monitoring picture or the snap-shot abnormal behavior picture to the database server 312, when the pedestrian features are screened, the pedestrian gender is selected through the application server, the skin color and the age are selected, the picture type and the orientation are selected, whether a cap is worn or not and a hair style is selected, the jacket type and the color are selected, the trousers type and the color are selected, the clothes texture and the backpack are selected, whether a mask is worn or not is selected, whether glasses are worn or not is selected, whether an umbrella is worn or not is selected, whether an object is carried or not is selected, whether a draw-bar box is provided or not is selected, whether a trolley is provided or not is selected, the accessed point location is selected, the checking time period is selected, after the checking is completed, the processor 2 can call out videos and pictures meeting conditions through the set adjustment, and accurate checking is achieved.
Example 3: the specific implementation mode of the AI traffic video analysis technology provided by the invention is as follows: the specific mode is that the application client 314 screens out the control information, inputs the license plate number, selects the license plate color, selects control personnel, selects the control point position and selects the control state to control.
Claims (9)
1. An AI traffic video analysis technique, characterized in that: comprises a hardware part and a software part;
the hardware part comprises a front-end monitoring device (1), a processor (2) and a monitoring application platform (3), the software part comprises a video structuring system (4), a vehicle identification system (5), an event identification system (6), a video concentrating system (7) and a traffic parameter system (8), the video structuring system (4) comprises a first target detection module (41), a target identification module (42) and a target tracking module (43), the vehicle identification system (5) comprises a vehicle identification module (51), a vehicle brand identification module (52), a vehicle type identification module (53) and a pedestrian and non-motor vehicle identification module (54), the event identification system (6) comprises an abnormal parking identification module (61), a vehicle reverse-driving identification module (62) and a pedestrian crossing identification module (63), and the video concentrating system (7) comprises a second target detection module (71), A trajectory tracking module (72), a trajectory optimization module (73) and a video compression module (74).
2. The AI traffic video analysis technique of claim 1, wherein: the processor (2) is an AI processor (2).
3. The AI traffic video analysis technique of claim 1, wherein: the data connection is established between the front-end monitoring equipment (1) and the processor (2), and the processor (2) and the monitoring application platform (3) are in data connection.
4. The AI traffic video analysis technique of claim 1, wherein: the first target detection module (41) adopts a target detection algorithm and is used for automatically detecting and positioning targets such as vehicles, non-motor vehicles, pedestrians and the like in the image;
the target identification module (42) adopts a target identification algorithm and is used for automatically detecting and identifying the attributes of the targets such as vehicles, non-motor vehicles, pedestrians and the like in the image;
the target tracking module (43) adopts a target tracking algorithm and is used for establishing a tracking track for detected targets such as motor vehicles, non-motor vehicles, pedestrians and the like and continuously tracking and analyzing the targets.
5. The AI traffic video analysis technique of claim 1, wherein: the vehicle recognition module (51) adopts a vehicle license plate recognition algorithm and is used for recognizing license plate numbers, license plate colors and license plate structures;
the vehicle brand identification module (52) employs a vehicle brand identification algorithm for identifying a vehicle brand;
the vehicle type identification module (53) adopts a vehicle type identification algorithm and is used for identifying vehicle types such as passenger cars, vans, trucks, passenger cars, motorcycles and the like;
the pedestrian and non-motor vehicle identification module (54) is used for identifying and providing identification capability of non-motor vehicles such as electric vehicles, bicycles, tricycles and pedestrians.
6. The AI traffic video analysis technique of claim 1, wherein: the abnormal parking identification module (61) adopts an abnormal parking detection algorithm and is used for setting thresholds such as abnormal parking response time, vehicle speed and the like, so that the abnormal parking detection requirements in different areas such as a traffic lane, an emergency lane and the like can be met;
the vehicle reverse-running recognition module (62) adopts a vehicle reverse-running detection algorithm and is used for setting threshold values such as vehicle reverse-running response time, vehicle speed and the like, so that the vehicle reverse-running detection requirements in different areas such as a running lane, an emergency lane and the like can be met;
the pedestrian crossing identification module (63) adopts a pedestrian crossing detection algorithm and is used for setting thresholds such as response time, walking speed and sensitivity of a pedestrian crossing event, and the pedestrian crossing detection requirements in different areas such as a traffic lane and an emergency lane can be met.
7. The AI traffic video analysis technique of claim 1, wherein: the traffic parameter system (8) comprises; a traffic flow module (81), a speed detection (82), an average time occupancy module (83), and a space occupancy module (84);
the traffic flow module (81) adopts a video coil-imitating algorithm and is used for automatically detecting and counting the traffic section and the lane flow of the road;
the speed detection (82) module adopts a video coil-tracing algorithm and is used for monitoring and statistically analyzing the speed of the vehicle passing through a section and a lane in real time;
the average time occupancy module (83) is used for calculating the percentage of the vehicle-on time and the vehicle-off time of the corresponding lane or section in the statistical time period;
the space occupancy rate module (84) is used for counting the percentage of the occupied space of the lane or the section vehicle and the occupied space of the vehicle without the vehicle in a time period.
8. The AI traffic video analysis technique of claim 1, wherein: the second target detection module (71) adopts algorithms such as motion detection, a background model, a scene model and the like, and is used for automatically detecting and extracting a motion target and other interested targets in an original image;
the trajectory tracking module (72) adopts a trajectory tracking algorithm and is used for establishing tracking trajectory data for the extracted target based on space-time logic, target running characteristics and the like;
the track optimization module (73) optimizes the running track of the concerned target by adopting a track optimization algorithm and is used for filtering factors such as environmental interference, invalid targets and the like;
the video compression module (74) adopts a video coding compression algorithm and is used for compressing the main target information and the effective image and generating a quick retrieval index picture so as to realize effective concentration processing on the original video.
9. The AI traffic video analysis technique of claim 1, wherein: the monitoring application center comprises a platform application subsystem (31), a GIS visual display module (32), an event visual module (33), a man-vehicle intelligent query module (34), a video retrieval module (35) and a traffic data visual module (36) which are used for providing service entrance for industrial clients based on applications such as video event and traffic perception, video structuring and video concentration, the platform application subsystem (31) comprises a data access server (311), a database server (312), a WEB application server (313), an application client (314) and an application end monitoring large screen (315), the data access server (311) realizes the collection and forwarding of front-end alarm event data, video records and traffic parameter data, the database server (312) realizes the storage and query support of the traffic events, the traffic parameter data and other data, the WEB application server (313) is used for deploying application platform server programs and providing support for data access and the like of the application client (314).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111437012.7A CN114140719A (en) | 2021-11-29 | 2021-11-29 | AI traffic video analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111437012.7A CN114140719A (en) | 2021-11-29 | 2021-11-29 | AI traffic video analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114140719A true CN114140719A (en) | 2022-03-04 |
Family
ID=80389346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111437012.7A Pending CN114140719A (en) | 2021-11-29 | 2021-11-29 | AI traffic video analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114140719A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783182A (en) * | 2022-04-14 | 2022-07-22 | 图为信息科技(深圳)有限公司 | Vehicle monitoring method and system based on edge calculation |
| CN114973663A (en) * | 2022-05-16 | 2022-08-30 | 浙江机电职业技术学院 | An intelligent roadside unit device based on edge computing |
| CN115731705A (en) * | 2022-11-03 | 2023-03-03 | 苏州中亿丰科技有限公司 | Vehicle-road cooperative system based on video structuring technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081844A (en) * | 2011-01-25 | 2011-06-01 | 华中科技大学 | Traffic video behavior analyzing and alarming server |
| CN107424412A (en) * | 2017-09-21 | 2017-12-01 | 程丹秋 | A kind of traffic behavior analysis system |
| CN111949811A (en) * | 2020-08-05 | 2020-11-17 | 深圳市中和智通智能科技有限公司 | Vision analysis data sharing system based on smart city |
| CN112580548A (en) * | 2020-12-24 | 2021-03-30 | 北京睿芯高通量科技有限公司 | Video concentration system and method in novel intelligent security system |
-
2021
- 2021-11-29 CN CN202111437012.7A patent/CN114140719A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081844A (en) * | 2011-01-25 | 2011-06-01 | 华中科技大学 | Traffic video behavior analyzing and alarming server |
| CN107424412A (en) * | 2017-09-21 | 2017-12-01 | 程丹秋 | A kind of traffic behavior analysis system |
| CN111949811A (en) * | 2020-08-05 | 2020-11-17 | 深圳市中和智通智能科技有限公司 | Vision analysis data sharing system based on smart city |
| CN112580548A (en) * | 2020-12-24 | 2021-03-30 | 北京睿芯高通量科技有限公司 | Video concentration system and method in novel intelligent security system |
Non-Patent Citations (3)
| Title |
|---|
| 于德新主编: "《交通工程学》", 31 January 2019, 北京理工大学出版社, pages: 72 * |
| 杨兆升: "《城市智能公共交通系统理论与方法》", 31 December 2004, 中国铁道出版社, pages: 156 * |
| 鞠全勇等: "《物联网技术与应用》", 30 June 2021, 吉林科学技术出版社, pages: 224 - 226 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783182A (en) * | 2022-04-14 | 2022-07-22 | 图为信息科技(深圳)有限公司 | Vehicle monitoring method and system based on edge calculation |
| CN114973663A (en) * | 2022-05-16 | 2022-08-30 | 浙江机电职业技术学院 | An intelligent roadside unit device based on edge computing |
| CN114973663B (en) * | 2022-05-16 | 2023-08-29 | 浙江机电职业技术学院 | Intelligent road side unit device based on edge calculation |
| CN115731705A (en) * | 2022-11-03 | 2023-03-03 | 苏州中亿丰科技有限公司 | Vehicle-road cooperative system based on video structuring technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112101433B (en) | Automatic lane-dividing vehicle counting method based on YOLO V4 and DeepSORT | |
| CN109784162B (en) | Pedestrian behavior recognition and trajectory tracking method | |
| Cai et al. | Deep learning-based video system for accurate and real-time parking measurement | |
| CN110428522B (en) | Intelligent security system of wisdom new town | |
| CN114140719A (en) | AI traffic video analysis technology | |
| Gawande et al. | Pedestrian detection and tracking in video surveillance system: issues, comprehensive review, and challenges | |
| CN110660222B (en) | Intelligent environment-friendly electronic snapshot system for black-smoke road vehicle | |
| Valera et al. | Intelligent distributed surveillance systems: a review | |
| CN116824859B (en) | Intelligent traffic big data analysis system based on Internet of things | |
| Albiol et al. | Detection of parked vehicles using spatiotemporal maps | |
| CN110874362A (en) | Data association analysis method and device | |
| CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
| CN107301776A (en) | Track road conditions processing and dissemination method based on video detection technology | |
| CN109615864A (en) | Vehicle congestion analysis method, system, terminal and storage medium based on video structural | |
| TWI450207B (en) | Method, system, computer program product and computer-readable recording medium for object tracking | |
| CN108710827B (en) | A kind of micro- police service inspection in community and information automatic analysis system and method | |
| CN110288738B (en) | Intelligent comprehensive management and control system and method for bicycle lane | |
| US20040249848A1 (en) | Method and apparatus for intelligent and automatic alert management using multimedia database system | |
| CN112651293A (en) | Video detection method for road illegal stall setting event | |
| CN117037040A (en) | Pedestrian recognition and tracking method based on multi-camera monitoring network | |
| CN1133138C (en) | Automatic traffic video image treating system | |
| Li et al. | RETRACTED: Intelligent transportation video tracking technology based on computer and image processing technology | |
| CN112188167B (en) | Method and system for video concentration, extraction, refinement and sublimation based on 5G edge cloud computing | |
| CN115909223B (en) | A method and system for matching WIM system information with surveillance video data | |
| CN117495896A (en) | Method and system for detecting abnormal track of pedestrian in traffic environment |
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 |