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

Search research articles

Related Experiment Video

Updated: May 10, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Laplacian eigenmap with temporal constraints for local abnormality detection in crowded scenes.

Myo Thida, How-Lung Eng, Paolo Remagnino

IEEE Transactions on Cybernetics

|June 13, 2013

Summary

Detecting abnormal crowd activities is crucial. This study introduces a spatiotemporal Laplacian eigenmap method for robust abnormal event detection and localization in crowded videos, offering computational simplicity.

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

Automated retinal image analysis systems to triage for grading of diabetic retinopathy: a large-scale, open-label, national screening programme in England.

The Lancet. Digital health·2025

Same author

Artificial vision models for the identification of Mediterranean flora: An analysis in four ecosystems.

PloS one·2025

Same author

Role of Artificial Intelligence in Detecting and Classifying Aortic Dissection: Where Are We? A Systematic Review and Meta-Analysis.

Radiology. Cardiothoracic imaging·2025

Same author

Ethnic disparities in progression rates for sight-threatening diabetic retinopathy in diabetic eye screening: a population-based retrospective cohort study.

BMJ open diabetes research & care·2023

Same author

Enhanced Single Shot Small Object Detector for Aerial Imagery Using Super-Resolution, Feature Fusion and Deconvolution.

Sensors (Basel, Switzerland)·2022

Same author

Image collection and annotation platforms to establish a multi-source database of oral lesions.

Oral diseases·2022

Area of Science:

Computer Vision
Artificial Intelligence
Pattern Recognition

Background:

Crowded scenes present unique challenges for activity recognition.
Detecting and localizing abnormal events in real-time is critical for public safety and security.
Existing methods often struggle with the complexity and scale of crowded environments.

Purpose of the Study:

To propose a novel method for detecting and localizing abnormal activities in crowded scenes.
To develop a computationally simple yet effective approach for analyzing crowd behavior.
To accurately identify and pinpoint anomalous events within video data.

Main Methods:

A spatiotemporal Laplacian eigenmap method is employed to learn spatial and temporal variations of local motions.

Related Experiment Videos

Last Updated: May 10, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

A model characterizing regular crowd behavior is constructed using representatives of different activities.

This model enables the detection of abnormal activities in both local and global contexts.

Main Results:

The proposed method effectively detects and localizes abnormal crowd activities.
Experimental results demonstrate comparable performance to state-of-the-art methods.
The approach maintains computational simplicity, making it practical for real-world applications.

Conclusions:

The spatiotemporal Laplacian eigenmap method offers a promising solution for abnormal crowd activity analysis.
The technique provides accurate detection and localization capabilities.
The method's computational efficiency makes it a viable option for real-time surveillance systems.