Abstract:

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 of a linear Support Vector Machine classi-
er. This is achieved by creating an integral image of the components of
the SVM which can readily obtain the classication score for any image
sub-window with only 10 additions and 2 products, regardless of its size.
Besides, we evaluated the performance of two ecient feature quantiza-
tion 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 compu-
tational cost.

• Tagged
• XML
• BibTex