Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Detection method of crowd flow anomaly events in monitoring video of congested scenes

A technology for monitoring video and crowded scenes, applied in the field of computer vision, it can solve the problems of dynamic occlusion, development into catastrophic events, and crowd flow has not yet been retrieved, and achieve the effect of improving stability

Active Publication Date: 2017-05-31
LIAONING TECHNICAL UNIVERSITY
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, no literature reports related to crowd flow anomaly detection for early warning of abnormal events have been retrieved.
The abnormal crowd flow to be detected here does not necessarily correspond to the ongoing safety accident, but there are potential dangers in it, and it is very likely to develop into a catastrophic event
In crowded crowded scenes, the movement of individuals is usually unpredictable. In addition, crowding will also bring serious dynamic occlusion. Therefore, abnormal detection of crowd flow is challenging, and a method is urgently needed to solve the above problems.

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
  • Detection method of crowd flow anomaly events in monitoring video of congested scenes
  • Detection method of crowd flow anomaly events in monitoring video of congested scenes
  • Detection method of crowd flow anomaly events in monitoring video of congested scenes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Take a video recording an irregularly surging crowded crowd as an example, in which a video frame such as figure 1 As shown in , a method for detecting abnormal crowd flow events in surveillance videos of crowded scenes is elaborated in detail, and the process is as follows figure 2 As shown, the specific process is as follows.

[0047] Step 1: Extract track segments from surveillance video. The trajectory of a particle in a video clip 480×360×600 is expressed as {(x(t), y(t))|x∈[1,480], y∈[1,360], t∈[1,600 ]};

[0048] Among them, the vector (x(t), y(t)) represents the position of the particle (x, y) at time t. image 3 for figure 1 The optical flow field of the crowd-flow video shown, Figure 4 It is the particle motion track of the video clip, and the track segment of the crowd flow gradually moves from dark to light. It can be seen from the figure that the particle trajectory shows the movement changes of the crowd flow in time and space, that is, the movement ...

Embodiment 2

[0072] A method for detecting abnormal crowd flow events in surveillance videos of crowded scenes, taking 10 videos of different scenes as examples to further verify the effectiveness of the method of the present invention. The resolution of these videos ranges from 480×360 to 720×480, and the frame rate ranges from 10fps (frames per second) to 25fps, including 5 segments of normal and abnormal crowd flow, such as Figure 10 As shown, the left column is the streaming videos of abnormal crowds, and the right column is the streaming videos of normal crowds. Figure 10 The first video of the anomaly group in the middle left column records irregularly surging crowds; the second video comes from the crowd flow segmentation data set, in which crowd flows from different directions are intertwined; the third video shows pedestrian crossings Pedestrians at opposite ends of the road cross the road; the fourth video records Muslims participating in the Hajj pilgrimage circling the "Kabba...

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 provides a detection method of crowd flow anomaly events in monitoring a video of congested scenes, and relates to the technical field of computer vision. The method comprises the steps of firstly, obtaining a short trajectory segment of particle motion through correlating the light streams between multiple continuous frames; using the hierarchical clustering algorithm to cluster the unstable light stream trajectory segments to make adjacent and similar trajectory segments concentrate to become small areas with statistical significance and enhance the reliability of motion description; finally, detecting crowd flow anomaly events through calculating the main direction and motion scope of the particles in the small areas to provide pre-warning to potential safety accidents. According to the detection method of crowd flow anomaly events in monitoring video of congested scenes, the clustering of the particle trajectory segments can make a single unreliable particle trajectory able to be co-used with peripheral similar particle trajectory to describe the crowd flow motion and enhance the stability of motion description. Tests are carried out on monitoring videos of actual scenes, the result indicates that the method can effectively detect the crowd flow anomaly events, and the results of the clustering of divided trajectory segments have a strong adaptability.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for detecting abnormal crowd flow events in a crowded scene monitoring video. Background technique [0002] With the continuous development of my country's economy, the level of urbanization has been significantly improved, and many large public places, such as: large shopping malls, theaters, stadiums, exhibition halls, etc. have been built accordingly. Corresponding large-scale social activities such as culture and sports are also increasing day by day, resulting in frequent public safety accidents such as congestion and stampede in large-scale activities. [0003] From the occurrence process of the crowd stampede accident, it can be seen that the safety management of places and activities with a large flow of people not only needs to monitor the density and flow of the crowd, but also needs to analyze and judge the flow direction and hedging situation of the c...

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): G06K9/00G06K9/62
CPCG06V20/44G06V20/53G06V20/46G06V20/40G06F18/231G06F18/22
Inventor 张新君李铁张新峰
Owner LIAONING TECHNICAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com