[-] Show simple item record

dc.contributor.advisorHan, Tony X.en_US
dc.contributor.authorChen, Guang
dc.date.issued2011
dc.date.submitted2011 Fallen_US
dc.descriptionTitle from PDF of title page (University of Missouri--Columbia, viewed on June 6, 2012).en_US
dc.descriptionThe entire thesis text is included in the research.pf file; the official abstract appears in the short.pf file; a non-technical public abstract appears in the public.pf file.en_US
dc.descriptionThesis advisor: Dr. Tony X. Hanen_US
dc.descriptionIncludes bibliographical references.en_US
dc.descriptionM.S. University of Missouri-Columbia 2011.en_US
dc.descriptionDissertations, Academic -- University of Missouri--Columbia -- Electrical engineering.en_US
dc.description"December 2011"en_US
dc.description.abstractFor object detection, the state-of-the-art performance is achieved through supervised learning. The performances of object detectors of this kind are mainly determined by two factors: features and underlying classification algorithms. In this work, we aim at improving the performance of object detectors from the aspect of classification algorithm. Observing the fact that classifiers used for object detection are task dependent and data driven, we developed a hybrid learning algorithm combining global classification and local adaptations, which automatically adjusts model complexity according to data distribution. We divide data samples into two groups, easy samples and ambiguous samples, using a learned global classifier. A local adaptation approach based on spectral clustering and proposed Min-Max model adaptation is then applied to further process the ambiguous samples. The proposed algorithm automatically determines model complexity of the local learning algorithm according to the distribution of ambiguous samples. By autonomously striking a balance between model complexity and learning capacity, the proposed hybrid learning algorithm incarnates a human detector outperforming the state-of-the-art algorithms on a couple of benchmark datasets and a self-collected pedestrian dataset. Besides, the proposed Min-Max model adaptation algorithm also successfully improve the performance of an offline-trained classifier on-site by adapting the classifier towards newly acquired data, without worries about the tuning the adaptation rate parameter, which affects the performance gain substantially. Taking the object detection as a testbed, we implement an adapted object detector based on binary classification. Under different adaptation scenarios and different datasets including PASCAL, ImageNet, INRIA, and TUD Pedestrian, the proposed adaption method achieves significant performance gain and is compared favorably with the state-of-the-art adaptation method with the fine tuned adaptation rate.en_US
dc.format.extentviii, 46 pagesen_US
dc.identifier.otherChenG-121611-T493
dc.identifier.urihttp://hdl.handle.net/10355/14534
dc.publisherUniversity of Missouri--Columbiaen_US
dc.relation.ispartof2011 Freely available theses (MU)en_US
dc.relation.ispartofcommunityUniversity of Missouri-Columbia. Graduate School. Theses and Dissertations. Theses. 2011 Theses
dc.subjectobject detectionen_US
dc.subjectclassifier cascadeen_US
dc.subjectlocal learningen_US
dc.subjecthybrid learningen_US
dc.titleObject detection with large intra-class variationen_US
dc.typeThesisen_US
thesis.degree.disciplineElectrical engineeringen_US
thesis.degree.grantorUniversity of Missouri--Columbiaen_US
thesis.degree.levelMastersen_US
thesis.degree.nameM.S.en_US


Files in this item

[PDF]
[PDF]
[PDF]

This item appears in the following Collection(s)

[-] Show simple item record