Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models
Authors:
- 31 December 2008
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 31 (3) , 539-555
Abstract
We propose a novel unsupervised learning framework to model activities and interactions in crowded and complicated scenes. Hierarchical Bayesian models are used to connect three elements in visual surveillance: low-level visual features, simple "atomic" activities, and interactions. Atomic activities are modeled as distributions over low-level visual features, and multi-agent interactions are modeled as distributions over atomic activities. These models are learnt in an unsupervised way. Given a long video sequence, moving pixels are clustered into different atomic activities and short video clips are clustered into different interactions. In this paper, we propose three hierarchical Bayesian models, Latent Dirichlet Allocation (LDA) mixture model, Hierarchical Dirichlet Process (HDP) mixture model, and Dual Hierarchical Dirichlet Processes (Dual-HDP) model. They advance existing language models, such as LDA [1] and HDP [2]. Our data sets are challenging video sequences from crowded traffic scenes and train station scenes with many kinds of activities co-occurring. Without tracking and human labeling effort, our framework completes many challenging visual surveillance tasks of board interest such as: (1) discovering typical atomic activities and interactions; (2) segmenting long video sequences into different interactions; (3) segmenting motions into different activities; (4) detecting abnormality; and (5) supporting high-level queries on activities and interactions.Keywords
This publication has 34 references indexed in Scilit:
- Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words2006
- Space-Time Behavior Based Correlation2005
- Actions as space-time shapes2005
- Discovering objects and their location in images2005
- Video behaviour profiling and abnormality detection without manual labelling2005
- TemporalBoost for event recognition2005
- Space-time interest points2003
- The representation and recognition of human movement using temporal templates2002
- View-Invariant Representation and Recognition of ActionsInternational Journal of Computer Vision, 2002
- 10.1162/jmlr.2003.3.4-5.993Applied Physics Letters, 2000