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

Crowd Abnormal Event Detection Method Based on Hypothesis Testing

A technology for hypothesis testing and abnormal events, which is applied to computer parts, instruments, calculations, etc., can solve the problems that crowd abnormal event detection algorithms cannot be processed in real time, model detection takes time and high computational complexity, and achieves time complexity optimization, The effect of reducing complexity and good robustness

Active Publication Date: 2019-03-01
HANGZHOU DIANZI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although there are many methods for crowd abnormal event detection, most crowd abnormal event detection algorithms cannot be processed in real time. The main difficulty lies in the time-consuming model detection and high computational complexity.

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
  • Crowd Abnormal Event Detection Method Based on Hypothesis Testing
  • Crowd Abnormal Event Detection Method Based on Hypothesis Testing
  • Crowd Abnormal Event Detection Method Based on Hypothesis Testing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The specific embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0061] Such as figure 1 Shown is the method of crowd abnormal event detection based on hypothesis testing. For the crowd abnormal event detection based on the global scene, the specific steps are described as follows figure 1 Shown:

[0062] Step 1: Preprocessing.

[0063] First decode the video frame from the video stream, and then perform Gaussian filtering on each video frame. The specific operation is: use a template to scan each pixel in the video frame, and use the template to determine the weighted average gray value of the pixels in the neighborhood. And replace the value of the center pixel of the template with the weighted average gray value.

[0064] The template, or convolution, mask, is a matrix of 0 and 1 with a size of N*N;

[0065] Step 2: Feature extraction.

[0066] Taking the video frame after Gaussian filte...

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 relates to a detection method for abnormal events based on crowds, in particular to a detection method based on medium-density crowds. The present invention captures the motion information of the crowd by using the optical flow method, thereby obtaining the motion feature descriptor of the crowd; for each video frame, the feature vector of each pixel is extracted, and the statistical method of hypothesis testing is used to perform the motion feature descriptor based on the motion feature descriptor. Then, compare the statistical value calculated by the hypothesis testing model with the threshold, so as to detect the occurrence of abnormal events. The invention not only omits cumbersome preprocessing steps in the feature extraction stage, but also uses a hypothesis testing model in the detection stage to greatly reduce the time complexity and calculation complexity of the detection stage without reducing the detection results. The present invention is not only applicable to global abnormal event detection, but also applicable to local abnormal event detection.

Description

technical field [0001] The invention relates to a method for detecting abnormal crowd events in public places, in particular to a method for detecting abnormal crowd events based on hypothesis testing. Background technique [0002] In recent years, security issues in public places have become increasingly prominent, and the requirements for intelligent monitoring have also become higher and higher. Therefore, video analysis technology has become a research hotspot in many countries. With the deepening and systematization of video analysis technology research, more and more More problems also emerged. One of the important issues is how to effectively monitor the crowd in public areas. For this reason, various technologies have been developed in various intelligent monitoring related fields. Among them, the development of video-based abnormal crowd event detection technology is particularly rapid. This technology can detect abnormal events in the monitoring area in time, imp...

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
CPCG06V20/53
Inventor 徐向华吕艳艳李平
Owner HANGZHOU DIANZI UNIV
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