ROBUST TECHNIQUES FOR VISUAL SURVEILLANCE

Simple item page
dc.contributor.advisorDavid, Larry Sen_US
dc.contributor.authorTran, Son Dinhen_US
dc.contributor.departmentComputer Scienceen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2008-10-11T05:44:11Z
dc.date.available2008-10-11T05:44:11Z
dc.date.issued2008-07-29en_US
dc.description.abstractThe work described here aims at improving the performance of three building blocks of visual surveillance systems: foreground detection, object tracking and event detection. First, a new background subtraction algorithm is presented for foreground detection. The background model is built with a set of codewords for every pixel. The codeword contains the pixel's principle color and a tangent vector that represents the color variation at that pixel. As the scene illumination changes, a pixel's color is predicted using a linear model of the codeword and the codeword, in turn, is updated using the new observation. We carried out a number of experiments on sequences that have extensive lighting change and compare with previously developed algorithms. Second, we describe a multi-resolution tracking framework developed with efficiency and robustness in mind. Efficiency is achieved by processing low resolution data whenever possible. Robustness results from multiple level coarse-to-fine searching in the tracking state space. We combine sequential filtering both in time and resolution levels int a probabilistic framework. A color blob tracker is implemented and the tracking results are evaluated in a number of experiments. Third, we present a tracking algorithm based on motion analysis of regional affine invariant image features. The tracked object is represented with a probabilistic occupancy map. Using this map as support, regional features are detected and matched across frames. The motion of pixels is then established based on the feature motion. The object occupancy map is in turn updated according to the pixel motion consistency. We describe experiments to measure the sensitivity of our approach to inaccuracy in initialization, and compare it with other approaches. Fourth, we address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited to overcome them. The knowledge is represented as first- order logic production rules with associated weights to indicate their confidence. These rules are used in combination with a relaxed deduction algorithm to construct a network of grounded atoms, the Markov Logic Network. The network is used to perform probabilistic inference for input queries about events of interest. The system's performance is demonstrated on a number of videos from a parking lot domain that contains complex interactions of people and vehicles.en_US
dc.format.extent34982576 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/8550
dc.language.isoen_US
dc.subject.pqcontrolledComputer Scienceen_US
dc.subject.pqcontrolledComputer Scienceen_US
dc.subject.pquncontrolledcomputer visionen_US
dc.subject.pquncontrolledobject trackingen_US
dc.subject.pquncontrolledvisual surveillanceen_US
dc.subject.pquncontrolledevent recognitionen_US
dc.subject.pquncontrolledbackground subtractionen_US
dc.titleROBUST TECHNIQUES FOR VISUAL SURVEILLANCEen_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
umi-umd-5634.pdf
Size:
33.36 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Computer Science Theses and Dissertations