Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Video-based non-supervision abnormal event real-time detection method

An abnormal event and real-time detection technology, applied in closed-circuit television systems, image data processing, instruments, etc., can solve the problems of manual threshold setting, complex feature extraction, and difficulty in meeting real-time requirements, achieving low complexity and simple features effective effect

Active Publication Date: 2016-01-06
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since this method uses multi-scale optical flow motion histograms as features, the feature extraction is more complicated, and it is difficult to meet the real-time requirements.
When modeling abnormal events, the sparse reconstruction method or clustering method is used, and the threshold needs to be manually set, which is difficult to apply to many occasions

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
  • Video-based non-supervision abnormal event real-time detection method
  • Video-based non-supervision abnormal event real-time detection method
  • Video-based non-supervision abnormal event real-time detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention can be divided into two stages of establishing abnormal event detection model and testing update. For real-time surveillance video, the current hour is selected as the training part to establish an abnormal event detection model, which can be divided into the following four steps:

[0027] Step 1: For a surveillance video with a frame rate of 25 frames per second, select 100 frames, that is, 4 seconds of video as a small video;

[0028] Step 2: For each small video, feature points are detected every 25 frames. The motion area is obtained by using the difference between frames and the background, and the edge feature points are extracted for the motion area, and the feature point step is 4. Or, directly detect feature points on the first frame of each small video.

[0029] Step 3: use the three-step search method to track the detected feature points, and extract the histograms of motion directions in 8 directions, the histograms of motion speed in...

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 video-based non-supervision abnormal event real-time detection method. Specific to the aims of reducing the quantity of inter-frame feature points and lowering the complexity in calculation of the feature points at the same time, the feature points are detected with an interval method, namely, a video is segmented, the feature points are detected on a first frame, and only tracking is required subsequently. The calculation amount of a tracking method is small relatively, so that the calculation complexity is lowered greatly. At the end of one segment of video, the feature points are detected once again. After the feature points of each video segment are obtained, direction, speed and location histograms of motion feature points are extracted and connected in series to serve as features of the video segments. Then, the features are subjected to Gaussian mixture modeling and updated in real time to obtain the probability of abnormal events in order to judge whether any abnormal event occurs or not. Thus, the abnormal events can be detected in real time.

Description

technical field [0001] The invention relates to video detection technology. Background technique [0002] With the development of social economy, people's demand for safety is also rising. Abnormal event detection, as an important part of the security monitoring system, has received widespread attention. The performance of the video monitoring system and the effectiveness of monitoring directly affect the overall effect of the security system. Abnormal event detection detects suspicious events in video files and automatically triggers alarms through automatic analysis and research on surveillance image files, and should be able to predict future events with a certain degree of reliability based on specific events in current video surveillance files Analysis verdict. The earliest video surveillance was mainly used for criminal investigation, and it was generally played back after the case occurred, requiring manual search for the situation when the incident occurred. Becau...

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 Applications(China)
IPC IPC(8): H04N7/18G06T7/20G06T7/40
Inventor 李宏亮马金秀杨德培罗雯怡侯兴怀姚梦琳李君涵
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
Eureka Blog
Learn More
PatSnap group products