Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models
Name
Wang-2009-Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models.pdf
Size
4.6 MB
Format
Adobe PDF
Checksum (MD5)
5cfac1766d6a66573451b72a857007a6
Author(s)
Wang, Xiaogang
Ma, Xiaoxu
Grimson, Eric
Date Issued
April 2008
Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Xiaogang Wang, Xiaoxu Ma, and W.E.L. Grimson. “Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models.” IEEE Transactions on Pattern Analysis and Machine Intelligence 31.3 (2009): 539–555. © Copyright 2009 IEEE
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/tpami.2008.87
