Share Email Print

Proceedings Paper

Towards behaviour recognition based video surveillance
Author(s): Shaogang Gong
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present the latest results on learnable stochastic temporal models for automatic event and behaviour recognition in CCTV surveillance video. We introduce a novel approach to modelling and recognising complex activities involving simultaneous movement of multiple objects. Our approach differs from most previous work in that the visual understanding of activity is based on visual event detection and reasoning instead of object tracking and trajectory matching. Dynamic probabilistic graph models are exploited for modelling the temporal relationships among a set of different object temporal events. Typical applications of this technology include automatic semantic video content analysis, profiling and indexing of salient event and behaviour captured in CCTV video, and the early recognition of atypical behaviour in scenes where such behaviour could lead to a threat to safety.

Paper Details

Date Published: 16 December 2004
PDF: 15 pages
Proc. SPIE 5616, Optics and Photonics for Counterterrorism and Crime Fighting, (16 December 2004); doi: 10.1117/12.577153
Show Author Affiliations
Shaogang Gong, Queen Mary Univ. of London (United Kingdom)

Published in SPIE Proceedings Vol. 5616:
Optics and Photonics for Counterterrorism and Crime Fighting
Tim P. Donaldson; Colin Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top