Group behavior recognition method and system

A recognition method and group technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problems of single pedestrian target segmentation, difficulty in target tracking, and limited effect of group behavior recognition. The effect of improving accuracy

Inactive Publication Date: 2021-12-21
JINAN RAILWAY TRANSPORT GRP CO LTD +1
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing group behavior recognition method mainly recognizes the behavior of the group by extracting the behavior characteristics of a single pedestrian. The inventors of the present disclosure found that in a complex scene, pedestrians block each other or block each other to target segmentation, Target tracking brings great difficulties, so the effect on group behavior recognition is limited

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
  • Group behavior recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Embodiment 1 of the present disclosure introduces a group behavior recognition method to improve the accuracy of group behavior recognition.

[0046] Such as figure 1 As shown, a group behavior recognition method includes:

[0047] Step S01: Obtain the video to be identified;

[0048] During specific implementation, the video to be recognized of the area to be recognized by the group behavior is acquired through the camera.

[0049] Step S02: Determine the group motion area of ​​the video to be identified;

[0050] In the specific implementation, the group motion information of two adjacent frames of the video to be identified is obtained through the improved adaptive background difference method;

[0051] The group motion information of two adjacent frames is integrated into the mixed Gaussian background model to eliminate the background information and the shadow of pedestrians in the previous frame, and the accurate and complete group motion area is obtained throu...

Embodiment 2

[0069] Embodiment 2 of the present disclosure introduces a group behavior recognition system.

[0070] A group behavior recognition system, comprising:

[0071] A video acquisition module, configured to acquire a video to be identified;

[0072] A motion area determination module is used to determine the group motion area of ​​the video to be identified;

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

The invention belongs to the technical field of behavior recognition, and provides a group behavior recognition method and system. The method comprises the steps: obtaining a to-be-recognized video; determining a group motion area of the to-be-recognized video; determining feature points through a target detection algorithm, tracking the feature points, connecting the feature points in space, and obtaining a spatial-temporal feature body description operator containing group interaction information; inputting the spatial-temporal feature body description operator into a behavior recognition model, and outputting a behavior recognition result, wherein the process of determining the feature points comprises the steps of extracting global features of each pedestrian and Upper features of the upper half face from the group motion area, fusing the global features of each pedestrian and the Upper features of the upper half face to obtain fused features of each pedestrian, and determining the feature points representing the pedestrians in the group motion area according to the fused features. The accuracy of group behavior recognition is improved.

Description

technical field [0001] The present disclosure relates to the technical field of behavior recognition, in particular to a group behavior recognition method and system. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] In recent years, with the rapid development of intelligent monitoring system and image processing technology, intelligent monitoring equipment has been widely installed in the field of public security, and the number is increasing year by year. At the same time, with the rapid development of the global economy, rapid social progress, and the continuous improvement of the comprehensive national strength of various countries, social security problems are becoming more and more serious, ranging from large public areas such as shopping malls and stations to small residential areas and school dormitories. The demand for real-time r...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06N3/045G06F18/253
Inventor 王伯芝门燕青曹玉鑫王晓晖谢浩王丰堃赵双聪
Owner JINAN RAILWAY TRANSPORT GRP CO LTD
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