Advanced Search
DSpace@MIT

Object Detection in Images by Components

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.author Mohan, Anuj en_US
dc.date.accessioned 2004-10-22T20:49:09Z
dc.date.available 2004-10-22T20:49:09Z
dc.date.issued 1999-08-11 en_US
dc.identifier.other AIM-1664 en_US
dc.identifier.other CBCL-178 en_US
dc.identifier.uri http://hdl.handle.net/1721.1/7293
dc.description.abstract In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure. en_US
dc.format.extent 22 p. en_US
dc.format.extent 8166715 bytes
dc.format.extent 2812392 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AIM-1664 en_US
dc.relation.ispartofseries CBCL-178 en_US
dc.subject AI en_US
dc.subject MIT en_US
dc.subject Artificial Intelligence en_US
dc.subject Object Detection en_US
dc.subject sComputer Vision en_US
dc.subject Pattern Recognition en_US
dc.subject Detection bysComponents en_US
dc.subject Machine Learning en_US
dc.subject People Detection en_US
dc.subject sWavelets en_US
dc.subject Detection of Partially Occluded Objects en_US
dc.subject sViewpoint Invariant Detection en_US
dc.subject Example Based Learnin en_US
dc.title Object Detection in Images by Components en_US


Files in this item

Name Size Format Description
AIM-1664.ps 7.788Mb Postscript
AIM-1664.pdf 2.682Mb PDF

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage