%0 Conference Proceedings
%T Efficient Object Pixel-Level Categorization using Bag of Features:  Advances in Visual Computing
%A David Aldavert
%A Ricardo Toledo
%A Arnau Ramisa
%A Ramon Lopez de Mantaras
%B 5th International Symposium on  Visual  Computing
%D 2009
%V 5875
%I Springer Berlin Heidelberg
%@ 0302-9743
%@ 978-3-642-10330-8
%F David Aldavert2009
%O ADAS
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1246), last updated on Tue, 29 Oct 2019 09:39:02 +0100
%X In this paper we present a pixel-level object categorization method suitable to be applied under real-time constraints. Since pixels are categorized using a bag of features scheme, the major bottleneck of such an approach would be the feature pooling in local histograms of visual words. Therefore, we propose to bypass this time-consuming step and directly obtain the score from a linear Support Vector Machine classifier. This is achieved by creating an integral image of the components of the SVM which can readily obtain the classification score for any image sub-window with only 10 additions and 2 products, regardless of its size. Besides, we evaluated the performance of two efficient feature quantization methods: the Hierarchical K-Means and the Extremely Randomized Forest. All experiments have been done in the Graz02 database, showing comparable, or even better results to related work with a lower computational cost.
%U https://doi.org/10.1007/978-3-642-10331-5_5
%U http://dx.doi.org/10.1007/978-3-642-10331-5_5
%P 44–55