CN110858400A - Method for tracking moving target through monitoring video - Google Patents
Method for tracking moving target through monitoring video Download PDFInfo
- Publication number
- CN110858400A CN110858400A CN201810957958.8A CN201810957958A CN110858400A CN 110858400 A CN110858400 A CN 110858400A CN 201810957958 A CN201810957958 A CN 201810957958A CN 110858400 A CN110858400 A CN 110858400A
- Authority
- CN
- China
- Prior art keywords
- target
- advancing
- video
- camera
- targets
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to a method for tracking a moving target through a monitoring video, which comprises the steps of selecting a camera in a designated area, and analyzing monitoring pictures of multiple paths of videos in real time; when alarming is carried out on a case, a camera nearby is searched through alarm positioning information, and a target person or a target vehicle is locked; searching a video structuralization result of the cameras in the peripheral range in batch, recording the longitude and latitude of the cameras in which the targets appear after the targets are found, continuously searching the structuralization result of the cameras in the periphery of the positions in which the targets appear according to the advancing direction and the advancing speed of the targets, and automatically drawing the advancing track of the targets on a map by combining the longitude and latitude of the positions in which the targets appear; pre-judging the position range of the target which is possible to appear in the next time period according to the direction and the speed of the target; and issuing the characteristics of the target, the track which appears and the position where the target appears to a surrounding policeman at the pre-judging position, and updating the advancing track of the target in real time.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to a method for tracking a moving target through a monitoring video, which is used in the aspects of public safety, public security video command and the like.
Background
The method comprises the following steps of intelligently analyzing an original video of a moving target, extracting key information and performing semantic description of a text, wherein the main extracted information comprises the following steps: first, identification of moving objects, whether the identification is a person or a vehicle; the second type is to identify the characteristics of the moving object, i.e. the characteristics of the moving person, vehicle and object in the picture, such as the sex, age, color of clothes, wearing glasses, etc. of the person, and identify the license plate, vehicle type, vehicle body color, etc. of the moving vehicle; and the third type is the identification of the moving target track, namely whether the person or the vehicle in the picture turns left or right or wanders.
Due to the limitations of technology and application level, moving object tracking has not fully exploited the application effect on "handling in the middle of events" when they occur. With the rapid development of computing such as cloud computing, big data, machine learning and the like, the video structuring technology is more perfect and superior in real-time analysis of massive videos and refined identification of target features, and has the condition of being applied to 'treatment in the middle of affairs', so that the treatment efficiency is improved.
Disclosure of Invention
The invention aims to provide a method for tracking a moving target by monitoring a video, which promotes the transition transfer of video research and judgment to the disposal of the event, realizes the guidance and command of video image research and judgment information results and improves the disposal efficiency.
The technical scheme of the invention is as follows:
a method for tracking a moving object through a surveillance video, characterized by:
(1) selecting a camera in a designated area, accessing a video structuring server, and analyzing monitoring pictures of multiple paths of videos in real time; the video structuring server identifies the characteristics and the track of multiple targets in one video, and necessary structured data comprise the characteristics, the advancing direction, the speed and the time of the targets;
(2) when alarming is carried out on a case, a camera nearby is searched through alarm positioning information, and a target person or a target vehicle is locked;
(3) searching a camera video structuralized result in a peripheral range in batch through structuralized target characteristics, advancing directions and advancing speeds, recording the longitude and latitude of a camera where a target appears after the target is found, continuously searching a camera structuralized result around the position where the target appears according to the advancing directions and speeds of the target, and automatically drawing an advancing track of the target on a map by combining the longitude and latitude of the position where the target appears;
(4) pre-judging the position range of the target which is possible to appear in the next time period according to the direction and the speed of the target;
(5) and issuing the characteristics of the target, the track which appears and the position where the target appears to a surrounding policeman at the pre-judging position, and updating the advancing track of the target in real time.
The invention utilizes the superior performance and the recognition effect of the current video structuring technology and combines the characteristics of the handling process of the public security organization case event, realizes the video tracking of the attention target in the case event occurrence process, provides real-time route guidance for rapid capture, and promotes the transition from 'post analysis' to 'handling in the case' of the public security organization video study and judgment.
Drawings
Fig. 1 is a schematic diagram of the information flow of the video tracking application of the present invention.
Detailed Description
As shown in fig. 1, the basic idea of the present invention is: after the alarm occurs in the case event, the peripheral videos are quickly searched according to the case event place, and the target vehicle or the target personnel are locked in real time. Under the condition of clear images and good video structuring results, the possible action tracks are measured and calculated in real time by using the video structuring analysis results according to the action direction and speed of the target, the peripheral video is automatically opened for searching, the adjacent video is quickly switched according to the motion condition of the target, and real-time video relay tracking is carried out; the video with fuzzy images and incapable of obtaining a relatively ideal video structural analysis result provides a function of quickly calling a real-time or historical video around a case place according to conditions such as time periods, road sections and the like, and provides a real-time video image for the police to perform deployment, control and enclosure. And the target track can be inquired in the historical video, so that the workload of manual checking is reduced.
After the target vehicle or the personnel are locked, the command center issues the target vehicle or the personnel image and the moving track or the moving range of the target to the surrounding policeman through the mobile APP, and the policeman is guided to carry out dynamic enclosure.
The specific implementation process of the invention is as follows:
(1) and selecting a camera in a designated area, accessing the camera to a video structured server, and analyzing the monitoring pictures of the multi-channel videos in real time. The video structuring server must be able to identify the features and trajectories of multiple targets in one video at the same time, and the necessary structured data includes the features, the forward direction, the speed and the time of the targets.
(2) When alarming is carried out on a case, a camera nearby is searched through the alarm positioning information, and a target person or a target vehicle is locked.
(3) And searching the camera video structuralized results in the peripheral range in batch through the structuralized target characteristics, the advancing direction and the advancing speed, recording the longitude and latitude (which are convenient for target positioning) of the camera in which the target appears after the target is found, and continuously searching the camera structuralized results in the periphery of the position in which the target appears according to the advancing direction and the advancing speed of the target. And automatically drawing the advancing track of the target on the map by combining the longitude and latitude of the position of the camera where the target appears.
(4) According to the direction and the speed of the target, the position range where the target can appear in the next time period (such as after 1 minute, after 5 minutes and the like) is judged in advance
(5) And issuing the characteristics of the target, the track which appears and the position where the target appears to a surrounding policeman at the pre-judging position, and updating the advancing track of the target in real time.
Claims (1)
1. A method for tracking a moving object through a surveillance video, characterized by:
(1) selecting a camera in a designated area, accessing a video structuring server, and analyzing monitoring pictures of multiple paths of videos in real time; the video structuring server identifies the characteristics and the track of multiple targets in one video, and necessary structured data comprise the characteristics, the advancing direction, the speed and the time of the targets;
(2) when alarming is carried out on a case, a camera nearby is searched through alarm positioning information, and a target person or a target vehicle is locked;
(3) searching a camera video structuralized result in a peripheral range in batch through structuralized target characteristics, advancing directions and advancing speeds, recording the longitude and latitude of a camera where a target appears after the target is found, continuously searching a camera structuralized result around the position where the target appears according to the advancing directions and speeds of the target, and automatically drawing an advancing track of the target on a map by combining the longitude and latitude of the position where the target appears;
(4) pre-judging the position range of the target which is possible to appear in the next time period according to the direction and the speed of the target;
(5) and issuing the characteristics of the target, the track which appears and the position where the target appears to a surrounding policeman at the pre-judging position, and updating the advancing track of the target in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810957958.8A CN110858400A (en) | 2018-08-22 | 2018-08-22 | Method for tracking moving target through monitoring video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810957958.8A CN110858400A (en) | 2018-08-22 | 2018-08-22 | Method for tracking moving target through monitoring video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110858400A true CN110858400A (en) | 2020-03-03 |
Family
ID=69635592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810957958.8A Pending CN110858400A (en) | 2018-08-22 | 2018-08-22 | Method for tracking moving target through monitoring video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110858400A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651690A (en) * | 2020-05-29 | 2020-09-11 | 深圳市天一智联科技有限公司 | Case-related information searching method and device and computer equipment |
| CN111784741A (en) * | 2020-06-29 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Method and system for target cross-mirror distribution control tracking |
| CN111818313A (en) * | 2020-08-28 | 2020-10-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Vehicle real-time tracking method and device based on monitoring video |
| CN112950674A (en) * | 2021-03-09 | 2021-06-11 | 厦门市公安局 | Cross-camera track tracking method and device based on cooperation of multiple identification technologies and storage medium |
| CN113837023A (en) * | 2021-09-02 | 2021-12-24 | 北京新橙智慧科技发展有限公司 | Cross-camera pedestrian automatic tracking method |
-
2018
- 2018-08-22 CN CN201810957958.8A patent/CN110858400A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651690A (en) * | 2020-05-29 | 2020-09-11 | 深圳市天一智联科技有限公司 | Case-related information searching method and device and computer equipment |
| CN111784741A (en) * | 2020-06-29 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Method and system for target cross-mirror distribution control tracking |
| CN111784741B (en) * | 2020-06-29 | 2024-03-29 | 杭州海康威视数字技术股份有限公司 | Method and system for target cross-mirror distributed tracking |
| CN111818313A (en) * | 2020-08-28 | 2020-10-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Vehicle real-time tracking method and device based on monitoring video |
| CN112950674A (en) * | 2021-03-09 | 2021-06-11 | 厦门市公安局 | Cross-camera track tracking method and device based on cooperation of multiple identification technologies and storage medium |
| CN112950674B (en) * | 2021-03-09 | 2024-03-05 | 厦门市公安局 | Cross-camera track tracking method and device based on cooperation of multiple recognition technologies and storage medium |
| CN113837023A (en) * | 2021-09-02 | 2021-12-24 | 北京新橙智慧科技发展有限公司 | Cross-camera pedestrian automatic tracking method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110858400A (en) | Method for tracking moving target through monitoring video | |
| US10930151B2 (en) | Roadside parking management method, device, and system based on multiple cameras | |
| Manju et al. | RETRACTED ARTICLE: Video analytics for semantic substance extraction using OpenCV in python | |
| CN109571468B (en) | Security inspection robot and security inspection method | |
| RU2316821C2 (en) | Method for automatic asymmetric detection of threat with usage of reverse direction tracking and behavioral analysis | |
| CN108040221B (en) | Intelligent video analysis and monitoring system | |
| Castellano et al. | Crowd detection in aerial images using spatial graphs and fully-convolutional neural networks | |
| CN102665071A (en) | Intelligent processing and search method for social security video monitoring images | |
| Gomaa et al. | Efficient vehicle detection and tracking strategy in aerial videos by employing morphological operations and feature points motion analysis | |
| CN112329691A (en) | Monitoring video analysis method and device, electronic equipment and storage medium | |
| CN109714565A (en) | A kind of video frequency tracking application method based on video structural technology | |
| KR101492473B1 (en) | Context-aware cctv intergrated managment system with user-based | |
| CN106557760A (en) | Monitoring system is filtered in a kind of image frame retrieval based on video identification technology | |
| Patel et al. | A survey on IoT based road traffic surveillance and accident detection system (A smart way to handle traffic and concerned problems) | |
| CN112257683A (en) | Cross-mirror tracking method for vehicle running track monitoring | |
| CN104469299A (en) | Network camera shooting device | |
| Chauhan et al. | Study of moving object detection and tracking for video surveillance | |
| Dominguez et al. | A GPU-accelerated LPR algorithm on broad vision survillance cameras | |
| Agarwal et al. | Suspicious Activity Detection in Surveillance Applications Using Slow-Fast Convolutional Neural Network | |
| CN110533889B (en) | Sensitive area electronic equipment monitoring and positioning device and method | |
| CN101286238A (en) | Bionic intelligent monitoring system | |
| KR20170095599A (en) | System and method for video searching | |
| Emiyah et al. | Extracting vehicle track information from unstabilized drone aerial videos using YOLOv4 common object detector and computer vision | |
| Dominguez et al. | Running License Plate Recognition (LPR) algorithms on smart survillance cameras. A feasibility analysis | |
| Lys et al. | Development of a Video Surveillance System for Motion Detection and Object Recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200303 |