Activity classification and anomaly detection using m-mediods based modelling of motion patterns

DOI10.1016/J.PATCOG.2010.05.006MaRDI QIDQ991992zbMATH OpenOpenAlexFDO

Authors Shehzad Khalid

Publication date 8 September 2010

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.patcog.2010.05.006

zbMATH Keywords

dimensionality reductionanomaly detectionevent miningmotion recognitionobject trajectorytrajectory modelling

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Recommendations

• Motion-based behaviour learning, profiling and classification in the presence of anomalies
• Spatiotemporal deformable prototypes for motion anomaly detection
• Activity based surveillance video content modelling
• Using dynamic Bayesian network for scene modeling and anomaly detection
• Detecting and discriminating behavioural anomalies

Cites work

• scientific article; zbMATH DE number 1717334 (Why is no real title available?)
• Motion-based behaviour learning, profiling and classification in the presence of anomalies

Cited in

(6)

• TOBAE: a density-based agglomerative clustering algorithm
• Crowd behavior analysis via curl and divergence of motion trajectories
• Spatiotemporal deformable prototypes for motion anomaly detection
• Motion-based behaviour learning, profiling and classification in the presence of anomalies
• Detecting and discriminating behavioural anomalies
• Frameworks for multivariate \(m\)-mediods based modeling and classification in Euclidean and general feature spaces

This page was built for publication: Activity classification and anomaly detection using \(m\)-mediods based modelling of motion patterns

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q991992)