Large-scale statistical modeling of motion patterns: A Bayesian nonparametric approach
|dc.identifier.citation||Rana, S. and Phung, D. and Pham, D. and Venkatesh, S. 2012. Large-scale statistical modeling of motion patterns: A Bayesian nonparametric approach, in Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing, Mumbai, India, Dec 16-19, 2012. ACM.|
We propose a novel framework for large-scale scene understanding in static camera surveillance. Our techniques combine fast rank-1 constrained robust PCA to compute the foreground, with non-parametric Bayesian models for inference. Clusters are extracted in foreground patterns using a joint multinomial+Gaussian Dirichlet process model (DPM). Since the multinomial distribution is normalized, the Gaussian mixture distinguishes between similar spatial patterns but different activity levels (eg. car vs bike). We propose a modification of the decayed MCMC technique for incremental inference, providing the ability to discover theoretically unlimited patterns in unbounded video streams. A promising by-product of our framework is online, abnormal activity detection. A benchmark video and two surveillance videos, with the longest being 140 hours long are used in our experiments. The patterns discovered are as informative as existing scene understanding algorithms. However, unlike existing work, we achieve near real-time execution and encouraging performance in abnormal activity detection. © 2012 ACM.
|dc.title||Large-scale statistical modeling of motion patterns: A Bayesian nonparametric approach|
|dcterms.source.title||Indian Conference on Computer Vision, Graphics and Image Processing|
|dcterms.source.series||ACM International Conference Proceeding Series|
|curtin.department||Multi-Sensor Proc & Content Analysis Institute|
|curtin.accessStatus||Fulltext not available|
Files in this item
There are no files associated with this item.