Recognition of group activities using dynamic probabilistic networks
- 1 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 742-749 vol.2
- https://doi.org/10.1109/iccv.2003.1238423
Abstract
Dynamic Probabilistic Networks (DPNs) are exploited for modeling the temporal relationships among a set of different object temporal events in the scene for a coherent and robust scene-level behaviour interpretation. In particular, we develop a Dynamically Multi-Linked Hidden Markov Model (DML-HMM) to interpret group activities involving multiple objects captured in an outdoor scene. The model is based on the discovery of salient dynamic interlinks among multiple temporal events using DPNs. Object temporal events are detected and labeled using Gaussian Mixture Models with automatic model order selection. A DML-HMM is built using Schwarz's Bayesian Information Criterion based factorisation resulting in its topology being intrinsically determined by the underlying causality and temporal order among different object events. Our experiments demonstrate that its performance on modelling group activities in a noisy outdoor scene is superior compared to that of a Multi-Observation Hidden Markov Model (MOHMM), a Parallel Hidden Markov Model (PaHMM) and a Coupled Hidden Markov Model (CHMM).Keywords
This publication has 12 references indexed in Scilit:
- The acquisition and use of interaction behaviour modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- VIGOUR: a system for tracking and recognition of multiple people and their activitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Autonomous Visual Events Detection and Classification without Explicit Object-Centred Segmentation and TrackingPublished by British Machine Vision Association and Society for Pattern Recognition ,2002
- A Framework for Recognizing the Simultaneous Aspects of American Sign LanguageComputer Vision and Image Understanding, 2001
- A Bayesian computer vision system for modeling human interactionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Learning patterns of activity using real-time trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Learning dynamic Bayesian networksPublished by Springer Nature ,1998
- Inference in belief networks: A procedural guideInternational Journal of Approximate Reasoning, 1996
- Visual surveillance in a dynamic and uncertain worldArtificial Intelligence, 1995
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978