Supercharge Your Innovation With Domain-Expert AI Agents!

Hierarchical clustering-based video abnormal event detection method

A technique of abnormal event and hierarchical clustering, which is applied to computer components, instruments, characters and pattern recognition, etc., can solve problems such as incomplete definitions of abnormal events and difficulties in abnormal event detection

Inactive Publication Date: 2019-11-19
TIANJIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in different scenarios, the definitions of abnormal events are not exactly the same, which brings certain difficulties to abnormal event detection

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
  • Hierarchical clustering-based video abnormal event detection method
  • Hierarchical clustering-based video abnormal event detection method
  • Hierarchical clustering-based video abnormal event detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The general research methods for abnormal event detection mainly include the following: abnormal detection based on probabilistic graphical model, such as applying Bayesian network and Markov random field to abnormal detection; abnormal detection based on deep learning, convolution Neural networks are used in anomaly detection; anomaly detection is performed based on dictionary learning and sparse representation, for example, K-SVD (K-singular value decomposition) and group sparse coding are applied to anomaly detection. The present invention uses a method based on dictionary learning and sparse representation for anomaly detection. In order to make sparse representation and dictionary learning more effective, the present invention applies hierarchical clustering to sparse coding, that is, the sparse coefficient matrix is ​​divided into blocks, and then the dictionary atoms corresponding to the sub-sparse matrices are condensed, and the block idea is simultaneously intro...

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 hierarchical clustering-based video abnormal event detection method. The method comprises the following steps: step 1, carrying out feature extraction; step 2, carrying outsparse coding based on hierarchical clustering and dictionary learning based on BK-SVD decomposition; step 3, carrying out abnormality judgment; step 4, carrying out training.

Description

technical field [0001] The invention belongs to the technical fields of image and video processing and computer vision, and relates to a method for detecting abnormal video events based on hierarchical clustering and applying dictionary learning and sparse representation. Background technique [0002] Video abnormal event detection is to judge whether there are abnormal events in the video, and it is a commonly used video processing application. However, in different scenarios, the definitions of abnormal events are not completely the same, which brings certain difficulties to abnormal event detection. [0003] Therefore, in different scenarios, the research objects for anomaly monitoring may be different, such as trajectories, crowds, etc. In sparse scenes, due to the absence of occlusion and other problems, the complexity of features is not high (this complexity generally refers to the dimension of features), and it is more robust to detect abnormalities by analyzing moti...

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
CPCG06V20/44G06V20/48G06V20/41G06V20/46G06F18/28
Inventor 侯春萍赵春月王致芃李北辰
Owner TIANJIN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com