Show simple item record

dc.contributor.advisorEric Grimsonen_US
dc.contributor.authorGrimson, Ericen_US
dc.contributor.authorWang, Xiaogangen_US
dc.contributor.authorNg, Gee-Wahen_US
dc.contributor.authorMa, Keng Tecken_US
dc.contributor.otherVisionen_US
dc.date.accessioned2008-03-17T19:15:17Z
dc.date.available2008-03-17T19:15:17Z
dc.date.issued2008-06-24
dc.identifier.otherMIT-CSAIL-TR-2008-015en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/40808
dc.description.abstractWe propose a novel nonparametric Bayesian model, Dual Hierarchical Dirichlet Processes (Dual-HDP), for trajectory analysis and semantic region modeling in surveillance settings, in an unsupervised way. In our approach, trajectories are treated as documents and observations of an object on a trajectory are treated as words in a document. Trajectories are clustered into different activities. Abnormal trajectories are detected as samples with low likelihoods. The semantic regions, which are intersections of paths commonly taken by objects, related to activities in the scene are also modeled. Dual-HDP advances the existing Hierarchical Dirichlet Processes (HDP) language model. HDP only clusters co-occurring words from documents into topics and automatically decides the number of topics. Dual-HDP co-clusters both words and documents. It learns both the numbers of word topics and document clusters from data. Under our problem settings, HDP only clusters observations of objects, while Dual-HDP clusters both observations and trajectories. Experiments are evaluated on two data sets, radar tracks collected from a maritime port and visual tracks collected from a parking lot.en_US
dc.format.extent12 p.en_US
dc.relationMassachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratoryen_US
dc.relationen_US
dc.subjecthierarchical Dirichlet processes, activity analysis, clustering, visual surveillanceen_US
dc.titleTrajectory Analysis and Semantic Region Modeling Using A Nonparametric Bayesian Modelen_US


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record