PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Feature Sets and Dimensionality Reduction for Visual Object Detection
Sibt ul Hussain and William Triggs
In: British Machine Vision Conference, 31 Aug - 3 Sep 2010, Aberystwyth, U.K..


We describe a family of object detectors that provides state-of-the-art error rates on several important datasets including INRIA people and PASCAL VOC'06 and VOC'07. The method builds on a number of recent advances. It uses the Latent SVM learning framework and a rich visual feature set that incorporates Histogram of Oriented Gradient, Local Binary Pattern and Local Ternary Pattern descriptors. Partial Least Squares dimensionality reduction is included to speed the training of the basic classifier with no loss of accuracy, and to allow a two-stage quadratic classifier that further improves the results. We evaluate our methods and compare them to other recent ones on several datasets. Our basic root detectors outperform the single component part-based ones of Felzenszwalb et. al. on 9 of 10 classes of VOC'06 (12% increase in Mean Average Precision) and 11 of 20 classes of VOC'07 (7% increase in MAP). On the INRIA Person dataset, they increase the Average Precision by 12% relative to Dalal & Triggs.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:7168
Deposited By:William Triggs
Deposited On:07 March 2011