Learning a Family of Detectors


Show simple item record

dc.contributor.author Yuan, Quan en_US
dc.date.accessioned 2011-10-20T04:56:38Z
dc.date.available 2011-10-20T04:56:38Z
dc.date.issued 2009-06-30 en_US
dc.identifier.uri http://hdl.handle.net/2144/1746
dc.description.abstract Object detection and recognition are important problems in computer vision. The challenges of these problems come from the presence of noise, background clutter, large within class variations of the object class and limited training data. In addition, the computational complexity in the recognition process is also a concern in practice. In this thesis, we propose one approach to handle the problem of detecting an object class that exhibits large within-class variations, and a second approach to speed up the classification processes. In the first approach, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly solved with using a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. For applications where explicit parameterization of the within-class states is unavailable, a nonparametric formulation of the kernel can be constructed with a proper foreground distance/similarity measure. Detector training is accomplished via standard Support Vector Machine learning. The resulting detectors are tuned to specific variations in the foreground class. They also serve to evaluate hypotheses of the foreground state. When the image masks for foreground objects are provided in training, the detectors can also produce object segmentation. Methods for generating a representative sample set of detectors are proposed that can enable efficient detection and tracking. In addition, because individual detectors verify hypotheses of foreground state, they can also be incorporated in a tracking-by-detection frame work to recover foreground state in image sequences. To run the detectors efficiently at the online stage, an input-sensitive speedup strategy is proposed to select the most relevant detectors quickly. The proposed approach is tested on data sets of human hands, vehicles and human faces. On all data sets, the proposed approach achieves improved detection accuracy over the best competing approaches. In the second part of the thesis, we formulate a filter-and-refine scheme to speed up recognition processes. The binary outputs of the weak classifiers in a boosted detector are used to identify a small number of candidate foreground state hypotheses quickly via Hamming distance or weighted Hamming distance. The approach is evaluated in three applications: face recognition on the face recognition grand challenge version 2 data set, hand shape detection and parameter estimation on a hand data set, and vehicle detection and estimation of the view angle on a multi-pose vehicle data set. On all data sets, our approach is at least five times faster than simply evaluating all foreground state hypotheses with virtually no loss in classification accuracy. en_US
dc.language.iso en_US en_US
dc.publisher Boston University Computer Science Department en_US
dc.relation.ispartofseries BUCS Technical Reports;BUCS-TR-2009-022 en_US
dc.title Learning a Family of Detectors en_US
dc.type Technical Report en_US
etd.degree.name Doctor of Philosophy
etd.degree.level doctoral
etd.degree.discipline Computer Science
etd.degree.grantor Boston University

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search OpenBU

Advanced Search


Deposit Materials