Supercharge Your Innovation With Domain-Expert AI Agents!

Attitude flow-based fight behavior identification method

A recognition method and behavior technology, applied in character and pattern recognition, neural architecture, instruments, etc., can solve the problems of underreporting of fighting behaviors, hidden safety hazards, high labor costs, etc., to achieve efficient identification of fighting behaviors and avoid false positives or omissions reported effect

Active Publication Date: 2021-07-13
GUANGZHOU HUAWEI TOMORROW SOFTWARE TECH
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method not only brings a large labor cost, but also leads to under-reporting of fighting behavior when the personnel leave the post for a short time, or when the personnel sleeps on the post, which brings great safety hazards

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
  • Attitude flow-based fight behavior identification method
  • Attitude flow-based fight behavior identification method
  • Attitude flow-based fight behavior identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] A fighting behavior recognition method based on gesture flow, such as figure 1 As shown, the steps include:

[0071] Step 1. Collect video stream data in the area in real time, and analyze the video stream data in real time to obtain an image;

[0072] Step 2. According to the key point detection algorithm model, judge whether there is a person in the current frame image based on the image obtained by the real-time analysis in step 1. The image with the person is corresponding to obtain the key point information of the human body. According to the key point information of the human body and the corner point detection algorithm model The image is tracked to obtain the humanoid ID corresponding to the person in the image;

[0073] Step 3, calculate the change of the upper limb key points of the same human figure ID in the current frame and the image of the adjacent previous frame, and obtain the sum of angle changes; then save the sum of angle changes of each figure ID, ...

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 attitude flow-based fight behavior identification method. Intelligent recognition is performed on fighting behaviors through seven steps. Firstly, a human body key point sequence is obtained through a human body key point detection algorithm based on deep learning, a human body is tracked in combination with a traditional image algorithm, and whether fight behaviors exist or not is judged by conducting logic analysis on human body posture queues in continuous frames of a video flow. False report or missing report caused by false detection of a single-frame image can be avoided, and the identification method does not need to collect samples to train a fighting model, so that fight behaviors can be identified more efficiently.

Description

technical field [0001] The invention relates to the technical field of public safety management, in particular to a method for recognizing fighting behavior based on gesture flow. Background technique [0002] In order to efficiently respond to public safety accidents, deal with emergencies in a timely manner, and reduce crime rates, managers of various cities have stepped up efforts to build safe cities. Fighting is a kind of behavior that disturbs public order. Fighting and fighting may be suspected of committing the crime of aggravating or picking quarrels and provoking trouble. [0003] At present, for the safety monitoring of some public places, such as construction sites, residential areas, schools, and prisons, it is generally necessary to set up multiple monitoring systems to manually monitor the monitoring screen for a long time. Put a stop to this. This method not only brings a large labor cost, but also leads to under-reporting of fighting behavior when personne...

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): G06K9/00G06N3/04G06Q50/26
CPCG06Q50/26G06V40/20G06V20/44G06V20/46G06V20/41G06N3/045
Inventor 李静尚伟艺王荣秋李朝辉
Owner GUANGZHOU HUAWEI TOMORROW SOFTWARE TECH
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