Grid clustering analysis-based violence behavior detection method

A grid clustering and detection method technology, applied in the field of image processing, can solve the problems of large amount of calculation and poor versatility, and achieve the effect of fast response and high precision

Active Publication Date: 2017-09-22
GUANGZHOU UNIVERSITY
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] For the traditional means of using image processing to detect violent incidents, the core is often to judge the occurrence of violent incidents through templ

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
  • Grid clustering analysis-based violence behavior detection method
  • Grid clustering analysis-based violence behavior detection method
  • Grid clustering analysis-based violence behavior detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be further described in detail below in conjunction with the drawings and specific embodiments.

[0082] Such as figure 1 As shown, the present invention discloses a violent behavior detection method based on grid clustering analysis, and its main steps include 7 steps, namely acquisition of source image frame, image preprocessing, human body detection, optical flow tracking, optical flow Feature points are used for cluster analysis, moving object judgment, and violent event judgment. Each step is described in detail below.

[0083] 1. Acquisition of source picture frames: read the video stream from the camera device or existing video files, and obtain the source picture frames.

[0084] 2. Image preprocessing: denoise, smooth, gain, and grayscale the source image for subsequent...

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 grid clustering analysis-based violence behavior detection method. The method comprises the following steps of: S1, reading a video streaming from camera equipment or an existing video file, and obtaining source picture frames in the video streaming; S2, preprocessing the source picture frames; S3, detecting human bodies in the preprocessed source picture frames and framing out the detected human bodies; S4, obtaining optical flow feature points of the source picture frame and carrying out optical flow tracing on the optical flow feature points; S5, carrying out clustering analysis on the optical flow feature points to obtain moving objects in the image; S5, analyzing moving conditions of the moving objects; and S7, carrying out statistic on a degree of polymerization change trend of the moving objects in continuous image frames so as to judge the detection of violence incidents. According to the method, the degree of polymerization change trend among a plurality of moving objects is calculated through video image information, and human body detection is carried out to judge whether violence incidents occur or not.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting violent behavior based on grid clustering analysis. Background technique [0002] For the traditional means of using image processing to detect violent incidents, the core is often to judge the occurrence of violent incidents through template matching, learning models and other methods. Due to the complexity of violent incidents, this method may not be universally applicable. Good, but the calculation is heavy. In view of this situation, it is necessary to design a detection algorithm for the simplified violent event model. Contents of the invention [0003] In order to overcome the shortcomings and deficiencies of the existing technology, the present invention provides a method for detecting violent behavior based on grid clustering analysis, which calculates the change trend of aggregation degree among multiple moving objects through video ima...

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): G06K9/00G06K9/62G06T7/269
CPCG06T7/269G06T2207/20076G06T2207/10016G06V20/44G06V20/41G06F18/23G06F18/214
Inventor 伍冯洁黎梓毅黄文恺张建华张雨楠陈志德冯兆熙肖颖
Owner GUANGZHOU UNIVERSITY
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