CN111640309A - Swift vehicle detecting system - Google Patents
Swift vehicle detecting system Download PDFInfo
- Publication number
- CN111640309A CN111640309A CN202010443425.5A CN202010443425A CN111640309A CN 111640309 A CN111640309 A CN 111640309A CN 202010443425 A CN202010443425 A CN 202010443425A CN 111640309 A CN111640309 A CN 111640309A
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- image
- unit
- 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
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
- G08G1/054—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed photographing overspeeding vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a rapid vehicle detection system, which comprises: the system comprises a real-time video stream input unit, an intelligent target detection unit, a vehicle state judgment and early warning unit, a three-dimensional scene reconstruction unit and a data storage and calling unit; the real-time video stream input unit is used for acquiring monitoring real-time video streams of target vehicles at different angles and sending the monitoring real-time video streams to the target intelligent detection unit; the target intelligent detection unit is used for detecting whether a target in a monitoring area is a vehicle or not; the vehicle state judging and early warning unit is used for detecting whether vehicles in the monitoring area have abnormal behaviors of overspeed and stagnation or not and sending out warning information in time; the three-dimensional scene reconstruction unit is used for reconstructing and restoring the positions of the vehicle and the trace on the original scene of the accident; the data storage and calling unit is used for storing the monitoring video, the alarm information and the accident model, the detection is more accurate and reliable, the detection effect is better, and the real-time operation speed is improved.
Description
Technical Field
The invention relates to the technical field of vehicle detection, in particular to a rapid vehicle detection system.
Background
With the improvement of the technological level and the increase of traffic volume, more and more vehicles cause the phenomena of traffic pressure and frequent accidents, therefore, the monitoring management of the vehicles can effectively assist the traffic management department to analyze the accidents and track the vehicles.
In conclusion, the rapid vehicle detection system which has the advantages of more accurate and reliable detection, better detection effect and higher real-time calculation speed is provided, and the problem which needs to be solved by technical personnel in the field is urgently needed.
Disclosure of Invention
In view of the above-mentioned problems and needs, the present invention provides a fast vehicle detection system, which can solve the above-mentioned technical problems by adopting the following technical solutions.
In order to achieve the purpose, the invention provides the following technical scheme: a rapid vehicle detection system comprising: the system comprises a real-time video stream input unit, an intelligent target detection unit, a vehicle state judgment and early warning unit, a three-dimensional scene reconstruction unit and a data storage and calling unit;
the real-time video stream input unit is used for acquiring monitoring real-time video streams of target vehicles at different angles and sending the monitoring real-time video streams to the target intelligent detection unit, and comprises a multi-angle image acquisition module, a self-adaptive light compensation module and an automatic focal length adjustment module;
the intelligent target detection unit is used for detecting whether a target in a monitoring area is a vehicle or not, and comprises a data receiving module, an image correction module, an image processing module and a vehicle detection module;
the vehicle state judging and early warning unit is used for detecting whether vehicles in a monitoring area have overspeed and stagnation abnormal behaviors and sending out warning information in time, and comprises a timing module, a speed detecting module, a track drawing module and an abnormal warning output module, wherein the timing module is connected with the speed detecting module, and the speed detecting module and the track drawing module are connected with the abnormal warning output module;
the three-dimensional scene reconstruction unit is used for reconstructing and restoring the positions of the vehicles and the traces on the original scene of the accident, and comprises an image receiving module, a three-dimensional modeling module and a model output module;
the data storage and calling unit is used for storing the monitoring video, the alarm information and the accident model and comprises a model database, a cloud server and an association list.
Furthermore, the multi-angle image acquisition module comprises a plurality of shooting cameras, and the self-adaptive light compensation module and the automatic focal length adjustment module are connected with the shooting cameras to perform automatic light compensation and focal length adjustment on the shooting cameras.
Furthermore, the data receiving module receives video stream information sent by the multi-angle image acquisition module, carries out decompression conversion processing to obtain continuous video sequence images, the image correction module carries out distortion correction on the video sequence images and then sends the video sequence images to the image processing module, and the image processing module carries out preprocessing on the corrected images and then sends the corrected images to the vehicle detection module for target vehicle detection.
Furthermore, the preprocessing includes removing noise signals of the video sequence images and converting the noise signals into gray images, and finally performing median filtering and template contrast enhancement on the vehicle images.
Further, the target vehicle detection specifically includes: b (x, y, i) ═ n (F (x, y, i-1) -B (x, y, i-1)) + B (x, y, i-1) adopts a self-adaptive background updating algorithm to update the background according to a formula, wherein n is an updated weight, the background of the ith frame is related to the current frame image and the background of the previous frame, and the background difference is carried out on the preprocessed background image and the preprocessed video image; obtaining a background differential image, selecting a proper threshold value by a dynamic self-adaptive threshold value method, and judging whether a vehicle exists or not; when the vehicle is detected to exist, the number of the current image frames is recorded, an object corresponding to the vehicle is established, and then the next image frame is obtained for detection.
Furthermore, the timing module tracks and times vehicles appearing in a monitoring area, the speed detection module calculates the running speed of a target vehicle according to timing data of the timing module and judges whether behaviors of vehicle overspeed and abnormal stagnation occur or not, if the behaviors of vehicle overspeed and abnormal stagnation occur, an alarm signal is output through the abnormal alarm output module, the track drawing module continuously tracks the target vehicle by adopting a target tracking algorithm based on a Kalman filter, draws and analyzes tracks according to motion track data of the target vehicle, and stores track drawing and analyzing results to the data storage and calling unit.
Furthermore, the model database is connected with the model output module to store accident models, the model database and the association list are both connected with the cloud server, the association list associates timestamp information and geographic marking information with the alarm information and the accident models, and an operator can quickly inquire related information through the association list.
Furthermore, the image receiving module is connected with the image processing module to receive the preprocessed image and send the preprocessed image to the three-dimensional modeling module, and the three-dimensional modeling module carries out three-dimensional modeling and rendering on the image, carries out calibration on key trace parameters to restore the accident three-dimensional scene and sends the three-dimensional scene to the model database.
The invention has the advantages of more accurate and reliable vehicle detection of the video image, better detection effect, improved real-time operation speed, high adaptability, capability of warning abnormal vehicle behaviors in a monitoring area and carrying out three-dimensional reconstruction and restoration on accident sites with escaping and other conditions.
The following description of the preferred embodiments for carrying out the present invention will be made in detail with reference to the accompanying drawings so that the features and advantages of the present invention can be easily understood.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly described below. Wherein the drawings are only for purposes of illustrating some embodiments of the invention and are not to be construed as limiting the invention to all embodiments thereof.
FIG. 1 is a schematic diagram of the structure of a rapid vehicle inspection system according to the present invention.
Fig. 2 is a schematic view of a vehicle state determination flow in the present embodiment.
Fig. 3 is a schematic diagram illustrating specific steps of a video image processing flow in this embodiment.
Fig. 4 is a schematic diagram illustrating specific steps of the target vehicle detection process in this embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of specific embodiments of the present invention. Like reference symbols in the various drawings indicate like elements. It should be noted that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention.
The invention provides a rapid vehicle detection system which is more accurate and reliable in vehicle detection of video images, improves the real-time operation speed, has high adaptability, can warn abnormal vehicle behaviors in a monitoring area, and carries out three-dimensional reconstruction and restoration on accident sites with escape and other situations. As shown in fig. 1 to 4, the rapid vehicle detection system includes: real-time video stream input unit, target intelligent detection unit, vehicle state judge and early warning unit, three-dimensional scene rebuild unit and data storage call unit, wherein, real-time video stream input unit is used for gathering the real-time video stream of the advance control of different angle target vehicles and sends to target intelligent detection unit, real-time video stream input unit includes multi-angle image acquisition module, self-adaptation light compensation module and automatic focal length adjustment module, wherein, multi-angle image acquisition module includes a plurality of shooting cameras, self-adaptation light compensation module with automatic focal length adjustment module with a plurality of shooting cameras are connected right a plurality of shooting cameras carry out automatic light compensation and focal length adjustment. The data storage and calling unit is used for storing the monitoring video, the alarm information and the accident model and comprises a model database, a cloud server and an association list.
The intelligent target detection unit is used for detecting whether a target in a monitoring area is a vehicle or not, and comprises a data receiving module, an image correction module, an image processing module and a vehicle detection module. As shown in fig. 3, the video image processing flow specifically includes: 1. the data receiving module receives the video stream information sent by the multi-angle image acquisition module and carries out decompression conversion processing to obtain continuous video sequence images; 2. the image correction module carries out distortion correction on the video sequence image and then sends the video sequence image to the image processing module; 3. the image processing module is used for preprocessing the corrected image and then sending the preprocessed image to the vehicle detection module for target vehicle detection, wherein the preprocessing comprises the steps of firstly removing a noise signal of the video sequence image and converting the noise signal into a gray image, and finally carrying out median filtering and template contrast enhancement processing on the vehicle image.
As shown in fig. 4, the target vehicle detection specifically includes: s10, obtaining a background image model by weighted average of the video sequence images, updating the background by adopting an adaptive background updating algorithm according to a formula, wherein B (x, y, i) ═ n (F (x, y, i-1) -B (x, y, i-1)) + B (x, y, i-1), wherein n is an updated weight, the background of the ith frame is related to the current frame image and the background of the previous frame, and performing background difference on the preprocessed background image and the preprocessed video image; s20, obtaining a background differential image, selecting a proper threshold value by a dynamic self-adaptive threshold value method, and judging whether a vehicle exists or not; and S30, when the vehicle is detected to exist, recording the number of the current image frames, establishing an object corresponding to the vehicle, and acquiring the next image frame for detection.
The vehicle state judging and early warning unit is used for detecting whether vehicles in a monitoring area have overspeed and stagnation abnormal behaviors and sending out warning information in time, and comprises a timing module, a speed detecting module, a track drawing module and an abnormal warning output module, wherein the timing module is connected with the speed detecting module, and the speed detecting module and the track drawing module are connected with the abnormal warning output module. As shown in the vehicle state determination flowchart of fig. 2, the timing module performs tracking timing on a vehicle appearing in a monitored area, and the speed detection module calculates the running speed of the target vehicle according to the timing data of the timing module and determines whether behaviors of vehicle overspeed and abnormal stagnation occur, that is, whether the staying time in the monitored area exceeds a threshold T and whether the running speed of the target exceeds a speed threshold V; if the behaviors of vehicle overspeed and abnormal stagnation occur, an alarm signal is output through the abnormal alarm output module; the track drawing module is used for continuously tracking the target vehicle by adopting a target tracking algorithm based on a Kalman filter, drawing and analyzing the track according to the motion track data of the target vehicle and storing the drawing and analyzing result of the track to the data storage and calling unit. In the present embodiment, the threshold value of the stay time and the threshold value of the overspeed of the vehicle may be adjusted according to the actual use condition of the system, for example, it is determined that the vehicle is abnormal behavior when the speed of the vehicle is more than 5 minutes in the non-parking area or the speed exceeds 30Km/h in the crowd accumulation when the vehicle is running, or it is abnormal behavior of overspeed when the speed exceeds 80Km/h in the crowd-poor area.
The three-dimensional scene reconstruction unit is used for reconstructing and restoring positions of vehicles and traces on an original scene of an accident, and comprises an image receiving module, a three-dimensional modeling module and a model output module, wherein the image receiving module is connected with the image processing module to receive a preprocessed image and send the preprocessed image to the three-dimensional modeling module, and the three-dimensional modeling module is used for carrying out three-dimensional modeling and rendering on the image, calibrating key trace parameters and restoring the accident three-dimensional scene and sending the three-dimensional scene to the model database. The model database is connected with the model output module to store accident models, the model database and the association list are both connected with the cloud server, the association list is used for associating timestamp information and geographic marking information with the alarm information and the accident models, and operators can quickly inquire related information through the association list.
In the embodiment, a detection algorithm based on background difference is adopted to detect the vehicle, after the vehicle is detected, the vehicle is tracked, whether abnormal behaviors such as stagnation, overspeed and the like exist in the vehicle in a monitoring area is judged through a vehicle state judging and early warning unit, if the abnormal behaviors occur, an alarm prompt is timely carried out, the three-dimensional scene reconstruction unit can carry out three-dimensional reproduction on the scene situation of the accident according to pictures acquired by the multi-angle camera, and relevant basis is provided for better carrying out next accident investigation. In addition, because the video image is deformed due to the influence of factors such as a wide angle, light and the like in the acquisition process, the image needs to be preprocessed through a distortion correction algorithm and then analyzed in the next step.
It should be noted that the described embodiments of the invention are only preferred ways of implementing the invention, and that all obvious modifications, which are within the scope of the invention, are all included in the present general inventive concept.
Claims (8)
1. A rapid vehicle detection system, comprising: the system comprises a real-time video stream input unit, an intelligent target detection unit, a vehicle state judgment and early warning unit, a three-dimensional scene reconstruction unit and a data storage and calling unit;
the real-time video stream input unit is used for acquiring monitoring real-time video streams of target vehicles at different angles and sending the monitoring real-time video streams to the target intelligent detection unit, and comprises a multi-angle image acquisition module, a self-adaptive light compensation module and an automatic focal length adjustment module;
the intelligent target detection unit is used for detecting whether a target in a monitoring area is a vehicle or not, and comprises a data receiving module, an image correction module, an image processing module and a vehicle detection module;
the vehicle state judging and early warning unit is used for detecting whether vehicles in a monitoring area have overspeed and stagnation abnormal behaviors and sending out warning information in time, and comprises a timing module, a speed detecting module, a track drawing module and an abnormal warning output module, wherein the timing module is connected with the speed detecting module, and the speed detecting module and the track drawing module are connected with the abnormal warning output module;
the three-dimensional scene reconstruction unit is used for reconstructing and restoring the positions of the vehicles and the traces on the original scene of the accident, and comprises an image receiving module, a three-dimensional modeling module and a model output module;
the data storage and calling unit is used for storing the monitoring video, the alarm information and the accident model and comprises a model database, a cloud server and an association list.
2. The rapid vehicle detection system according to claim 1, wherein the multi-angle image acquisition module comprises a plurality of cameras, and the adaptive light compensation module and the automatic focus adjustment module are connected to the plurality of cameras for performing automatic light compensation and focus adjustment on the plurality of cameras.
3. The rapid vehicle detection system according to claim 2, wherein the data receiving module receives video stream information sent by the multi-angle image acquisition module, decompresses and converts the video stream information to obtain continuous video sequence images, the image correction module performs distortion correction on the video sequence images and sends the video sequence images to the image processing module, and the image processing module performs preprocessing on the corrected images and sends the video sequence images to the vehicle detection module for target vehicle detection.
4. The rapid vehicle detection system according to claim 3, wherein the preprocessing comprises removing noise signals of the video sequence images and converting the noise signals into gray images, and finally performing median filtering and template contrast enhancement on the vehicle images.
5. The rapid vehicle detection system according to claim 3, wherein the target vehicle detection specifically comprises: b (x, y, i) ═ n (F (x, y, i-1) -B (x, y, i-1)) + B (x, y, i-1) adopts a self-adaptive background updating algorithm to update the background according to a formula, wherein n is an updated weight, the background of the ith frame is related to the current frame image and the background of the previous frame, and the background difference is carried out on the preprocessed background image and the preprocessed video image; obtaining a background differential image, selecting a proper threshold value by a dynamic self-adaptive threshold value method, and judging whether a vehicle exists or not; when the vehicle is detected to exist, the number of the current image frames is recorded, an object corresponding to the vehicle is established, and then the next image frame is obtained for detection.
6. The rapid vehicle detection system according to claim 1, wherein the timing module tracks and times vehicles appearing in a monitored area, the speed detection module calculates the running speed of a target vehicle according to the timing data of the timing module and determines whether behaviors of vehicle overspeed and abnormal stagnation occur, if the behaviors of vehicle overspeed and abnormal stagnation occur, an alarm signal is output through the abnormal alarm output module, and the trajectory drawing module continuously tracks the target vehicle by using a target tracking algorithm based on a kalman filter, draws and analyzes a trajectory according to the movement trajectory data of the target vehicle, and stores the result of the trajectory drawing and analyzing to the data storage and calling unit.
7. The rapid vehicle detection system according to claim 1, wherein the model database is connected to the model output module to store accident models, the model database and the association list are both connected to the cloud server, the association list associates timestamp information and geotag information with the alarm information and the accident models, and an operator can query related information rapidly through the association list.
8. The rapid vehicle detection system according to claim 1, wherein the image receiving module is connected to the image processing module to receive the preprocessed image and send the preprocessed image to the three-dimensional modeling module, and the three-dimensional modeling module performs three-dimensional modeling and rendering on the image, calibrates the key trace parameters to restore the accident three-dimensional scene, and sends the calibrated key trace parameters to the model database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443425.5A CN111640309A (en) | 2020-05-22 | 2020-05-22 | Swift vehicle detecting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443425.5A CN111640309A (en) | 2020-05-22 | 2020-05-22 | Swift vehicle detecting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111640309A true CN111640309A (en) | 2020-09-08 |
Family
ID=72331426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010443425.5A Pending CN111640309A (en) | 2020-05-22 | 2020-05-22 | Swift vehicle detecting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111640309A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727672A (en) * | 2008-10-24 | 2010-06-09 | 云南正卓信息技术有限公司 | Method for detecting, tracking and identifying object abandoning/stealing event |
| CN101872546A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Video-based method for rapidly detecting transit vehicles |
| CN102722704A (en) * | 2012-06-12 | 2012-10-10 | 厦门宸天电子科技有限公司 | Method and system for recognizing vehicle license plate by integrating video dynamic tracking |
| CN103942533A (en) * | 2014-03-24 | 2014-07-23 | 河海大学常州校区 | Urban traffic illegal behavior detection method based on video monitoring system |
| US8947376B2 (en) * | 2010-10-01 | 2015-02-03 | Z124 | Desktop reveal expansion |
| CN104809874A (en) * | 2015-04-15 | 2015-07-29 | 东软集团股份有限公司 | Traffic accident detection method and device |
| CN105046731A (en) * | 2015-06-25 | 2015-11-11 | 西安理工大学 | Accident site virtual multi-attention-perspective conversion three-dimensional dynamic reproducing method |
| CN207068060U (en) * | 2017-05-16 | 2018-03-02 | 交通运输部公路科学研究所 | The scene of a traffic accident three-dimensional reconstruction system taken photo by plane based on unmanned plane aircraft |
| CN108335489A (en) * | 2018-03-11 | 2018-07-27 | 西安电子科技大学 | Vehicle on highway behavior semantic analysis and abnormal behaviour monitoring system and method |
| CN108596129A (en) * | 2018-04-28 | 2018-09-28 | 武汉盛信鸿通科技有限公司 | A kind of vehicle based on intelligent video analysis technology gets over line detecting method |
-
2020
- 2020-05-22 CN CN202010443425.5A patent/CN111640309A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727672A (en) * | 2008-10-24 | 2010-06-09 | 云南正卓信息技术有限公司 | Method for detecting, tracking and identifying object abandoning/stealing event |
| CN101872546A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Video-based method for rapidly detecting transit vehicles |
| US8947376B2 (en) * | 2010-10-01 | 2015-02-03 | Z124 | Desktop reveal expansion |
| CN102722704A (en) * | 2012-06-12 | 2012-10-10 | 厦门宸天电子科技有限公司 | Method and system for recognizing vehicle license plate by integrating video dynamic tracking |
| CN103942533A (en) * | 2014-03-24 | 2014-07-23 | 河海大学常州校区 | Urban traffic illegal behavior detection method based on video monitoring system |
| CN104809874A (en) * | 2015-04-15 | 2015-07-29 | 东软集团股份有限公司 | Traffic accident detection method and device |
| CN105046731A (en) * | 2015-06-25 | 2015-11-11 | 西安理工大学 | Accident site virtual multi-attention-perspective conversion three-dimensional dynamic reproducing method |
| CN207068060U (en) * | 2017-05-16 | 2018-03-02 | 交通运输部公路科学研究所 | The scene of a traffic accident three-dimensional reconstruction system taken photo by plane based on unmanned plane aircraft |
| CN108335489A (en) * | 2018-03-11 | 2018-07-27 | 西安电子科技大学 | Vehicle on highway behavior semantic analysis and abnormal behaviour monitoring system and method |
| CN108596129A (en) * | 2018-04-28 | 2018-09-28 | 武汉盛信鸿通科技有限公司 | A kind of vehicle based on intelligent video analysis technology gets over line detecting method |
Non-Patent Citations (2)
| Title |
|---|
| 衡威威: "基于近景摄影测量的交通事故", 《中国司法鉴定》 * |
| 过秀成，盛玉刚: "《公路交通事故黑点分析技术》", 31 March 2009 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110689054B (en) | Worker violation monitoring method | |
| CN109167997B (en) | Video quality diagnosis system and method | |
| EP2549738B1 (en) | Method and camera for determining an image adjustment parameter | |
| EP2549759B1 (en) | Method and system for facilitating color balance synchronization between a plurality of video cameras as well as method and system for obtaining object tracking between two or more video cameras | |
| CN103096121B (en) | A kind of camera movement detection method and device | |
| CN110781853B (en) | Crowd abnormality detection method and related device | |
| CN112528861A (en) | Foreign matter detection method and device applied to track bed in railway tunnel | |
| CN116385948B (en) | System and method for early warning railway side slope abnormality | |
| CN108174198B (en) | Video image quality diagnosis analysis detection device and application system | |
| CN112769877A (en) | Group fog early warning method, cloud server, vehicle and medium | |
| KR101987184B1 (en) | Intelligent transport system managing risk situation using VMS and CCTV | |
| CN111009136A (en) | Method, device and system for detecting vehicles with abnormal running speed on highway | |
| CN106781167A (en) | The method and apparatus of monitoring object motion state | |
| CN113947744A (en) | Fire image detection method, system, equipment and storage medium based on video | |
| CN111640309A (en) | Swift vehicle detecting system | |
| CN117475296A (en) | Real-time monitoring method and system for rural illegal building | |
| KR101581162B1 (en) | Automatic detection method, apparatus and system of flame, smoke and object movement based on real time images | |
| CN111369578A (en) | Intelligent tracking method and system for holder transaction | |
| CN106448163B (en) | Road monitoring method and road monitoring device | |
| KR100615672B1 (en) | Fire observation system using xy axis projection graph and its fire observation method and computer-readable recording medium to realize fire observation method | |
| JP3736836B2 (en) | Object detection method, object detection apparatus, and program | |
| CN110309838B (en) | Object contour detection preprocessing method for video detection area based on exponential transformation | |
| JP2002190027A (en) | System and method for measuring speed by image recognition | |
| CN110930362A (en) | Screw safety detection method, device and system | |
| CN115082571B (en) | Anomaly detection method and system for in-road parking camera |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200908 |