Robust Methods for Visual Tracking and Model Alignment

Simple item page
dc.contributor.advisorChellappa, Ramaen_US
dc.contributor.authorWu, Haoen_US
dc.contributor.departmentElectrical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2010-02-19T06:35:40Z
dc.date.available2010-02-19T06:35:40Z
dc.date.issued2009en_US
dc.description.abstractThe ubiquitous presence of cameras and camera networks needs the development of robust visual analytics algorithms. As the building block of many video visual surveillance tasks, a robust visual tracking algorithm plays an important role in achieving the goal of automatic and robust surveillance. In practice, it is critical to know when and where the tracking algorithm fails so that remedial measures can be taken to resume tracking. We propose a novel performance evaluation strategy for tracking systems using a time-reversed Markov chain. We also present a novel bidirectional tracker to achieve better robustness. Instead of looking only forward in the time domain, we incorporate both forward and backward processing of video frames using a time-reversibility constraint. When the objects of interest in surveillance applications have relatively stable structures, the parameterized shape model of objects can be usually built or learned from sample images, which allows us to perform more accurate tracking. We present a machine learning method to learn a scoring function without local extrema to guide the gradient descent/accent algorithm and find the optimal parameters of the shape model. These algorithms greatly improve the robustness of video analysis systems in practice.en_US
dc.identifier.urihttp://hdl.handle.net/1903/9827
dc.subject.pqcontrolledEngineering, Electronics and Electricalen_US
dc.subject.pqcontrolledComputer Scienceen_US
dc.subject.pquncontrolledboosted rankingen_US
dc.subject.pquncontrolledcomputer visionen_US
dc.subject.pquncontrolledmodel alignmenten_US
dc.subject.pquncontrolledparticle filteringen_US
dc.subject.pquncontrolledperformance evaluationen_US
dc.subject.pquncontrolledvisual trackingen_US
dc.titleRobust Methods for Visual Tracking and Model Alignmenten_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Wu_umd_0117E_10752.pdf
Size:
8.75 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Electrical & Computer Engineering Theses and Dissertations