Unlock instant, AI-driven research and patent intelligence for your innovation.

A Crowd Aggregation Behavior Detection Method Based on Grid Cell Features

A technology of grid cells and detection methods, applied in instruments, character and pattern recognition, computer parts, etc., can solve the problems of low detection accuracy and poor robustness.

Inactive Publication Date: 2018-01-12
CIVIL AVIATION UNIV OF CHINA
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods all have the disadvantages of low detection accuracy and poor robustness.

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 Crowd Aggregation Behavior Detection Method Based on Grid Cell Features
  • A Crowd Aggregation Behavior Detection Method Based on Grid Cell Features
  • A Crowd Aggregation Behavior Detection Method Based on Grid Cell Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The method for detecting crowd gathering behavior based on grid unit features provided by the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0025] Such as figure 1 As shown, the crowd gathering behavior detection method based on grid unit features provided by the present invention includes the following steps in order:

[0026] 1) For the video input, the mixed Gaussian model is used to extract the crowd foreground;

[0027] First of all, if figure 2 The video input shown is extracted using a Gaussian mixture model as image 3 Crowd foreground shown.

[0028] 2) adopt median filter to carry out median filter processing to above-mentioned obtained crowd prospect;

[0029] 3) The crowd foreground obtained in step 2) after median filter processing is pressed by Figure 4 The mesh division shown gives Figure 5 Shown is a grid with m*m pixel rectangular cells as the minimum unit, wherein ...

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

A crowd gathering behavior detection method based on grid cell features. It includes: using a mixed Gaussian model to extract the crowd foreground for the video input; performing median filter processing on the crowd foreground; dividing the crowd foreground into grids with m*m pixel rectangular cells as the minimum unit; Foreground pixel statistics are performed on each cell of the grid cell to obtain the grid cell feature map; the number of cells with a cell feature value of 1 in the grid cell feature map is counted; the search box is used to perform a global search on the grid cell feature map, Calculate the two-dimensional probability density; calculate the two-dimensional joint distribution entropy; calculate the crowd gathering behavior reference index; judge the crowd gathering behavior, if G>Go, it indicates that the crowd gathering behavior occurs and an alarm is issued. The method of the invention can effectively detect crowd gathering behavior, and can be widely used in public places with high public safety requirements such as squares, stations, and airports.

Description

technical field [0001] The invention belongs to the technical field of intelligent video monitoring, in particular to a method for detecting crowd gathering behavior based on grid unit characteristics. Background technique [0002] In recent years, with the frequent occurrence of group incidents, public safety is facing huge challenges, and crowd behavior analysis has attracted more and more attention. There are few studies on abnormal behaviors, such as crowd gathering behavior. Facts show that crowd gathering will be accompanied by other violent events, such as gang fights, so the research on crowd gathering behavior is of great significance. However, due to the complex and changeable crowd scenes in practice, the understanding of crowd gathering behavior is also ambiguous. [0003] Chinese Invention Patent No. 201410051592.X discloses a method for extracting crowd dynamic aggregation features. Chinese invention patent No. 201210071625.8 discloses a crowd gathering detec...

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): G06K9/00
Inventor 张良张朋跃
Owner CIVIL AVIATION UNIV OF CHINA