Method for detecting global and local abnormal behaviors in crowd scene

A local anomaly and detection method technology, applied in the field of image processing, can solve the problems of ignoring information differences, scattered abnormal behavior misdetection, etc.

Active Publication Date: 2017-12-19
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, and propose a global and local abnormal behavior detection method in crowd scenes, which solves the problem of ignoring the information differences between regions in the existing detection methods, and for scattered abnormal behaviors There is a problem of false detection

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
  • Method for detecting global and local abnormal behaviors in crowd scene
  • Method for detecting global and local abnormal behaviors in crowd scene
  • Method for detecting global and local abnormal behaviors in crowd scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The technical scheme of the present invention is described in detail below in conjunction with accompanying drawing:

[0060] The purpose of the present invention is to provide a new global and local abnormal behavior detection method, and its implementation idea is as follows: a new descriptor named feature of mixed optical flow histogram is proposed. For the detection of global abnormal behavior, there are two sparse processes, one to judge whether the area is normal, and the other to judge whether the area is abnormal. Each process has a process of dynamic dictionary update. The two sparse processes give two probabilities, and finally use fuzzy Integral processes these two judgments to get the final result of the region. For local abnormal behavior detection, the foreground of the region of interest is first extracted, and then detected by online weighted clustering, and the noise is filtered out by multi-target tracking. The method flow chart of the present inventi...

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 method for detecting global and local abnormal behaviors in a crowd scene. Firstly, features of a new mixed optical flow histogram are proposed; secondly, for the global abnormal behavior, a dual sparse representation method is proposed for solving the problem; and finally, for the local abnormal behavior, a foreground of a region of interest of a current frame is detected first and then the local abnormal behavior is detected by adopting an online weighted clustering method. Experiments in a UMN data set and a UCSD data set verify the advantages of the method. Experimental results show that the method has higher precision in analyzing motion behaviors of crowds in a video, compared with a previous method.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a global and local abnormal behavior detection method in a crowd scene. Background technique [0002] Video surveillance equipment has been widely used in public places such as traffic intersections, shops, banks, subway stations and schools to ensure social safety. With video surveillance it is easy to record the situation in the video monitored by the camera. However, with most existing monitoring systems, abnormal events cannot be checked automatically, and it is impossible for a person to monitor the monitors at all times. [0003] Since surveillance equipment is usually installed in public places, crowd behavior analysis has been a new hotspot in the field of computer vision research. Classical methods for individual behavior analysis cannot be used in crowded scenes due to the occlusion phenomenon. Video surveillance in crowded areas is playing an in...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/53G06F18/23
Inventor 金栋梁朱松豪邢晓远闫兴秀
Owner NANJING UNIV OF POSTS & TELECOMM
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap