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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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