Supercharge Your Innovation With Domain-Expert AI Agents!

A method for detecting fights in videos

A technology of video and histogram, applied in the field of video detection, can solve the problems of poor fight detection and false positives, achieve good results, reduce false positives, and improve accuracy

Inactive Publication Date: 2017-08-25
信帧机器人技术(北京)有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for complex light scenes, the traditional method of fighting detection is often not good, and a large number of false positives occur
If the detection threshold is increased, more false negatives will be caused

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
  • A method for detecting fights in videos

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] Such as figure 1 As shown, the detection method of fighting in the video of the present invention comprises the following steps:

[0015] (1) Effective feature point value acquisition: feature point detection, feature point motion estimation and quantification;

[0016] (2) Acquisition of violent motion blocks: divide the image into blocks, count the characteristic direction histogram of each block, and calculate the histogram entropy value. If the histogram entropy value exceeds a certain threshold, it is considered as a violent motion block;

[0017] (3) Cumulative strenuous motion score: when a block in a certain frame is a strenuous motion block, add a certain value to its strenuous motion score; if not, reduce the strenuous motion score of this block by a certain percentage;

[0018] (4) Connected area output of violent motion: If a certain violent credible value exceeds the set threshold, it is considered as a violent motion block, and the connected violent motio...

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 present invention provides a method for detecting fights in a video suitable for fight detection under complex light conditions, comprising the following steps: (1) obtaining effective feature point values: performing feature point detection, feature point motion estimation and quantification; 2) Acquisition of violent motion blocks: Divide the image into blocks, count the characteristic direction histogram of each block, and calculate the histogram entropy value. If the histogram entropy value exceeds a certain threshold, it is considered as a violent motion block; (3) Cumulative violent motion score: when When a certain block in a certain frame is a violent motion block, its violent motion score will be increased by a certain value; if not, the violent motion score of this block will be reduced by a certain percentage; (4) Connected area output of severe motion: if a block’s violent credible value exceeds the set If the threshold is set, it is considered as a severe motion block, and the connected violent motion blocks are formed into a connected area. If the area of ​​the connected area is greater than the set threshold, it will be output as a severe motion connected area.

Description

technical field [0001] The invention relates to a video detection method, in particular to a video detection method for fighting. Background technique [0002] In recent years, video surveillance technology has been more and more used in the security field. With the continuous growth of the amount of surveillance data, surveillance personnel need to spend a lot of time manually filtering the data and selecting useful video information from it. Repetitive work often overwhelms them. Surveillance personnel urgently need a product that is easier to work, easier to operate and manage to replace the original system. As a result, intelligent video technology came into being and entered people's lives. [0003] Intelligent video is the introduction of computer vision methods into intelligent monitoring. This technology includes automatic detection of moving or stationary targets, target classification and behavior understanding by video image sequences, the purpose is to establi...

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): H04N5/14H04N7/18
Inventor 刘忠轩
Owner 信帧机器人技术(北京)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com