Analyzing and recognizing method for abnormal behaviors in intelligent videos

A recognition method and technology in video, applied in the field of intelligent video analysis, can solve the problems that the security system is difficult to achieve early intervention and quickly process feedback updates, so as to achieve the effect of improving the level of intelligence

Inactive Publication Date: 2013-05-22
上海博超科技有限公司
View PDF7 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Many violent incidents in cities and campuses in recent years have made all walks of life aware of the importance of security; with the continuous development of high-definition, networking, and digitalization, security monitoring systems have been widely installed, and video surveillance data has grown at an alarming rate; Th

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
  • Analyzing and recognizing method for abnormal behaviors in intelligent videos
  • Analyzing and recognizing method for abnormal behaviors in intelligent videos
  • Analyzing and recognizing method for abnormal behaviors in intelligent videos

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention is an analysis and recognition method for abnormal behavior in intelligent video, the steps are as follows:

[0035] First, analyze the video surveillance images of the security system, especially the monitored scenarios and behaviors;

[0036] Secondly, determine the monitoring object and implement target detection;

[0037] Third, conduct behavior recognition based on the analysis of video surveillance data and target detection results.

[0038] Abnormal behavior recognition is divided into the following situations according to the space-time stage:

[0039] Enter and leave, appear and disappear, stop, hover, direction filter, tailgating. If it is not in these cases, it is classified as non-anomalous behavior.

[0040] According to attached figure 1 , video acquisition equipment such as gun camera, dome camera, etc. collect video data and input it into the intelligent video analysis box, and the intelligent video analysis box analyzes it. The...

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 an analyzing and recognizing method for abnormal behaviors in intelligent videos. The method includes: firstly, analyzing video monitoring images of a security system, especially monitored scenes and behaviors; secondly, determining monitoring objects, and implementing target detection; and thirdly, performing behavior recognition according to analysis results of video monitoring data and target detection results. Abnormal behavior recognition is divided into following circumstances according to space-time phases: entering, leaving, appearing, disappearing, stopping, fluctuating, direction filtering and shadowing. Circumstances not belonging to the above are classified into non-abnormal behaviors. By the analyzing and recognizing method for the abnormal behaviors in the intelligent videos, various behaviors can be defined, recognized and analyzed, and automatic analysis and automatic alarming are realized when preset abnormal behaviors occur, so that intelligentialized level of the security system is improved.

Description

technical field [0001] The invention relates to an intelligent video analysis technology, and in particular discloses an analysis and identification method for abnormal behavior in an intelligent video, which improves the intelligence level of a security system by intelligently analyzing and identifying the abnormal behavior in a surveillance video. Background technique [0002] Many violent incidents in cities and campuses in recent years have made all walks of life aware of the importance of security; with the continuous development of high-definition, networking, and digitalization, security monitoring systems have been widely installed, and video surveillance data has grown at an alarming rate; The construction needs of safe cities and the high standard requirements of urban emergency command make it difficult for ordinary security systems to achieve early intervention, rapid processing, and feedback updates. As an intelligent means, intelligent video analysis technology ...

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): G08B13/196H04N7/18
Inventor 晋胜国
Owner 上海博超科技有限公司
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