Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Group behavior analysis method based on multi-feature fusion

A technology of multi-feature fusion and behavior analysis, applied in the fields of instruments, character and pattern recognition, computer components, etc., can solve the problems of inability to distinguish slow-moving groups well, over-segmentation of low-density groups, etc.

Active Publication Date: 2018-04-24
SICHUAN UNIV
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Ali et al. used the Lagrangian quasi-order structure to segment motion patterns, revealing the potential fluid structure characteristics of the velocity field, but the disadvantage of this method is that it cannot distinguish slow-moving groups well, and may over-segment low-density ones. group

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 analysis method based on multi-feature fusion
  • Group behavior analysis method based on multi-feature fusion
  • Group behavior analysis method based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention will be further described below in conjunction with accompanying drawing:

[0064] Such as figure 1 As shown, the following steps are used to analyze the group behavior in the video.

[0065] (1) Group-level feature extraction

[0066] a. Input a video sequence image of τ frame, use cluster transformation method to detect and segment groups, and obtain a series of groups Each group contains a set of track segments {z} obtained by the KLT feature point tracking method.

[0067] b. For each detected group, it is necessary to extract a set of visual descriptors to represent its local motion information, that is, to calculate clustering, stability, consistency, and conflict feature descriptors in sequence.

[0068] (2) Multi-dimensional optical flow feature extraction

[0069] Input a video sequence image of τ frame, optimize the block processing first, and then calculate the multi-dimensional optical flow histogram features after 2×2 block, and r...

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 discloses a group behavior analysis method based on multi-feature fusion, and belongs to the field of machine vision and intelligent information processing. On one hand, the method researches the group behavior characteristics of a group level, one series of feature descriptors which represent local movement information can be extracted, wherein the feature descriptors comprise gregariousness, stability, consistency and conflict; on the other hand, the method imports a new multidimensional optical flow histogram feature to represent the global movement information, and a multilayer dictionary learning method to carry out further optimization; and finally, through a local movement feature descriptor and a global movement feature descriptor are fused to form a feature set whichcan comprehensively describe group behaviors, and the method can be applied to aspects including group behavior analysis, behavior recognition and the like. The rationality and the effectiveness of the method can be proved through experiments on a real video library.

Description

technical field [0001] The invention relates to a group movement research method, in particular to a group behavior analysis method based on multi-feature fusion, which belongs to the field of machine vision and intelligent information processing. Background technique [0002] Group sports are ubiquitous in nature, with various types and scales. Group movement widely exists in various group systems, for example, the movement of galaxies formed by the aggregation of celestial bodies, the activities of organisms such as ant colonies, and the group behavior of crowds in public places. In real life, the analysis and research of group movement has brought a series of key applications in visual surveillance, crowd management and other related fields, including crowd flow statistics and congestion analysis, anomaly detection and alarm, development of crowd management strategies, etc. . [0003] The technical extraction of group behavior analysis methods based on multi-feature fus...

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): G06K9/62G06K9/00
CPCG06V20/46G06V20/41G06F18/23213G06F18/23G06F18/2411G06F18/253
Inventor 何小海刘文璨卿粼波滕奇志吴晓红单倩文王正勇
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com