Target tracking method and system, personnel behavior analysis method and system

A target tracking and target technology, which is applied in image analysis, closed-circuit television system, image enhancement, etc., can solve the problems of high camera installation requirements, difficult target classification, and difficult tracking, and achieve good adaptability, easy function improvement and expansion, Wide range of effects

Active Publication Date: 2019-04-30
SUZHOU KEDA TECH +2
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] For this reason, the technical problem to be solved by the present invention lies in the personnel detection and tracking method based on face detection, head and shoulders detection or whole body detection, which may easily cause false positives, missed negatives, difficult tracking, etc. As a result, and it has high requirements for the erection of cameras, a method and system for target tracking based on head detection, and a method and system for analyzing human behavior are proposed.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Target tracking method and system, personnel behavior analysis method and system
  • Target tracking method and system, personnel behavior analysis method and system
  • Target tracking method and system, personnel behavior analysis method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0083] like figure 1 As shown, this embodiment provides a target tracking method, which includes the following steps:

[0084] S11: use a camera to acquire video images;

[0085] S12: Detect the candidate head target in the current image by using the front head classifier, the back head classifier, the left head classifier and the right head classifier, respectively.

[0086] S13: De-duplication and screening of candidate head targets detected by each classifier;

[0087] S14: delete the head target that does not meet the tracking conditions;

[0088] S15: Track the remaining head targets respectively.

[0089] Since the human head is relatively round and has the characteristics of rotation invariance, the angle adaptability of the human head is the best, and the requirements for camera erection are low. In this method, the angle between the erection direction and the horizontal plane is greater than 0 degrees and less than 60 degrees. All video streams captured by cameras...

Embodiment 2

[0120] like Figure 4 As shown, this embodiment provides a personnel behavior analysis method, including:

[0121] S21: Use the target tracking method described in Embodiment 1 to track the human head target in the video image obtained by the camera;

[0122] S22: According to the tracking results, conduct behavior analysis on the personnel corresponding to each head target, including counting the number of personnel; and / or, analyzing the density of personnel; and / or, counting the number of personnel in various directions; and / or, counting the given time Pedestrian heat in the interior; analyze the abnormal behavior of personnel, including wandering, running, lingering, crossing the line, being alone, falling to the ground abnormally, and entering and leaving designated areas.

[0123] specifically:

[0124] The number of statistical personnel refers to: accurately count the number of personnel in the designated area or the whole screen according to the detection and tracki...

Embodiment 3

[0165] like Figure 5 As shown, this embodiment provides a target tracking system, including:

[0166] Image acquisition unit U1: used to acquire video images by using a camera;

[0167] Detection unit U2: used to detect the candidate head target in the current image by using the front head classifier, the back head classifier, the left head classifier and the right head classifier respectively;

[0168] Deduplication and screening unit U3: used to deduplicate and screen the candidate head targets detected by each classifier;

[0169]Tracking target screening unit U4: used to delete head targets that do not meet the tracking conditions;

[0170] Tracking unit U5: used to track the remaining human head targets respectively.

[0171] Since the angle adaptability of the human head is the best, and the requirements for camera erection are low, the target tracking system provided in this embodiment is applicable to the video stream collected by the camera where the angle between...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A target tracking method and system, and a personnel behavior analysis method and system, wherein the target tracking method includes the following steps: using a camera to obtain a video image; using a front head classifier, a back head classifier, a left head classifier, and a head classifier respectively. The head classifier on the right side detects candidate head targets in the current image; deduplicates and screens candidate head targets detected by each classifier; deletes head targets that do not meet the tracking conditions; and tracks the remaining head targets separately. Solved the detection and tracking methods based on face detection, head shoulder detection or whole body detection, which are easy to cause false positives, missed negatives, difficult tracking due to easy occlusion, difficult target classification and other reasons, as well as its erection requirements for cameras high technical problems. The present invention can not only accurately track personnel trajectories based on head targets, reduce target re-reporting problems, but also perform personnel behavior analysis based on tracking results.

Description

technical field [0001] The present invention relates to the technical field of video surveillance. Specifically, it relates to a target tracking method and system, and a personnel behavior analysis method and system. Background technique [0002] With the rapid development of society and economy, the application of video surveillance systems in various industries is gradually maturing, and the number of cameras built and put into use is increasing rapidly. How to effectively use these cameras to better maintain social stability and harmony, monitor individual behaviors in public places, and eliminate all kinds of illegal and extreme behaviors in the bud has become an imminent problem for law enforcement departments in the entire society. . [0003] Since the surveillance system collects a large number of videos, the real-time monitoring of these videos has gradually become a big problem. Authoritative data shows that people's attention can only last for 20 minutes, and mo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T7/20H04N7/18
CPCH04N7/18G06T2207/30196G06V20/53
Inventor 张全磊晋兆龙陈卫东张天益徐文才
Owner SUZHOU KEDA TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products