PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Fast SVM Approximations for Object Detection
Wolf Kienzle, Matthias Franz and Bernhard Schölkopf
In: Pattern Recognition and Machine Learning in Computer Vision Workshop, 03 - 05 May 2004, Grenoble, France.


It has been shown that Support Vector Machines (SVMs) provide state-of-the-art accuracies in object detection. However, for real time applications, standard SVMs are usually too slow. In this work, we propose a method for approximating an SVM detector in terms of a small number of separable nonlinear filters. We are building on work of Romdhani et al. (ICCV 2001), where an SVM face detector was approximated using the so-called reduced set algorithm and evaluated in a cascade. However, when using plain gray values as features, we found it more effective to reduce the high computational cost for the pixel-wise comparisons, rather than focusing on sparsity of the detectors alone. In our approach, we constrain the reduced set optimization to a class of nonlinear convolution filters which can be evaluated more efficiently (i.e. O(w+h) instead of O(wh), where w and h are the patch dimensions, respectively). We demonstrate a prototype of our system which runs in real time on a standard PC.

EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:368
Deposited By:Wolf Kienzle
Deposited On:18 December 2004