Object detection and tracking using a parts-based approach

Show simple item record

dc.contributor.advisor Gaborski, Roger en_US
dc.contributor.author Clark, Daniel
dc.date.accessioned 2005-11-21T18:30:39Z
dc.date.accessioned 2006-03-09T21:14:19Z
dc.date.available 2005-11-21T18:30:39Z en_US
dc.date.available 2006-03-09T21:14:19Z en_US
dc.date.issued 2005
dc.identifier.uri http://hdl.handle.net/1850/1167
dc.description.abstract One of the main goals of artificial intelligence is to allow computers to understand the world around them. As humans we extract a large amount of knowledge about the world from our visual perception, and the field of computer vision is determined to give computers access to this same wealth of knowledge. One of the fundamental steps in understanding the world is finding specific objects within our field of view, and the related task of following these objects as they move. In this thesis the Implicit Shape Model algorithm, a local feature-based object detection algorithm, is implemented and used to develop an appearance model and object tracking algorithm based on it. This algorithm is very robust to intraclass variation, and can successfully track objects when both occlusion and non-stationary backgrounds are present. The usefulness of the proposed appearance model is analyzed, and results of the algorithm on real video sequences are presented. Several enhancements to the method are also proposed, and performance in terms of recall and precision is analyzed.
dc.format.extent 288502 bytes en_US
dc.format.extent 1282278 bytes en_US
dc.format.extent 81001 bytes en_US
dc.format.extent 102 bytes en_US
dc.format.extent 2061 bytes en_US
dc.format.extent 688 bytes en_US
dc.format.extent 6350 bytes en_US
dc.format.extent 43 bytes en_US
dc.format.extent 288502 bytes en_US
dc.format.extent 1282278 bytes en_US
dc.format.mimetype application/pdf en_US
dc.format.mimetype application/pdf en_US
dc.format.mimetype text/plain en_US
dc.format.mimetype text/plain en_US
dc.format.mimetype text/plain en_US
dc.format.mimetype application/octet-stream en_US
dc.format.mimetype application/octet-stream en_US
dc.format.mimetype application/octet-stream en_US
dc.format.mimetype application/pdf en_US
dc.format.mimetype application/pdf en_US
dc.language.iso en_US
dc.subject Algorithm en_US
dc.subject Artificial Intelligence en_US
dc.subject Computer Vision en_US
dc.subject Implicit Shape en_US
dc.subject Object Detection en_US
dc.subject Visual Perception en_US
dc.subject.lcc TA1634 .C54 2005
dc.subject.lcsh Computer vision
dc.subject.lcsh Optical pattern recognition
dc.subject.lcsh Pattern recognition systems
dc.subject.lcsh Automatic tracking
dc.subject.lcsh Image processing
dc.subject.lcsh Detectors
dc.title Object detection and tracking using a parts-based approach
dc.type Thesis
dc.description.college Golisano College of Computing and Information Sciences
dc.description.department Computer Science
dc.description.approval 2005-09

Files in this item

Files Size Format View
DClarkThesis092005.pdf 1.282Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse