Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Taking Astray Domain Back Home for Single-Source Domain Generalizable Text-to-Image Person Retrieval.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Hybrid AI Pipeline for Laboratory Detection of Internal Potato Defects Using 2D RGB Imaging.

Journal of imaging·2025

Same author

Understanding the Dimensional Need of Noncontrastive Learning.

IEEE transactions on cybernetics·2025

Same author

Improving Text-Based Person Retrieval by Excavating All-Round Information Beyond Color.

IEEE transactions on neural networks and learning systems·2024

Same author

Synchronous Spatiotemporal Graph Transformer: A New Framework for Traffic Data Prediction.

IEEE transactions on neural networks and learning systems·2022

Same author

End-to-End Deep One-Class Learning for Anomaly Detection in UAV Video Stream.

Journal of imaging·2021

Search research articles

Related Experiment Video

Updated: May 4, 2026

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Online least squares one-class support vector machines-based abnormal visual event detection.

Tian Wang¹, Jie Chen, Yi Zhou

¹Institut Charles Delaunay-LM2S-UMR STMR 6279 CNRS, University of Technology of Troyes, Troyes 10004, France. wangtian8704@gmail.com.

Sensors (Basel, Switzerland)

|December 20, 2013

Summary

This summary is machine-generated.

This study introduces an online one-class classification algorithm for real-time abnormal event detection in video surveillance. The novel online least squares one-class support vector machine (online LS-OC-SVM) effectively identifies unusual events by modeling normal behavior.

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Related Experiment Videos

Last Updated: May 4, 2026

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Abnormal event detection is crucial for real-time video surveillance.
Existing methods may struggle with dynamic and evolving normal behavior patterns.

Purpose of the Study:

To propose a novel online one-class classification algorithm for efficient abnormal event detection.
To develop a sparsified version for improved model complexity control.

Main Methods:

The study introduces the online least squares one-class support vector machine (online LS-OC-SVM).
A sparsified version (sparse online LS-OC-SVM) is proposed, controlling model complexity via a coherence criterion.
Video frames are characterized by covariance matrix descriptors encoding motion information.

Main Results:

The online LS-OC-SVM method demonstrates promising results in detecting abnormal events.
Experiments on synthetic and benchmark datasets validate the algorithm's effectiveness.
The algorithm successfully classifies video frames as normal or abnormal.

Conclusions:

The proposed online LS-OC-SVM algorithm is effective for real-time abnormal event detection in video surveillance.
The method provides an efficient way to model normal behavior and detect deviations.
The sparsified version offers a way to manage model complexity in online learning scenarios.