Material Detail

Fast SVM Approximations for Object Detection

Fast SVM Approximations for Object Detection

This video was recorded at Workshop on Pattern Recognition and Machine Learning in Computer Vision, Grenoble 2004. 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.


  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.