a hierarchical compositional strongsystemstrong for rapid object.pdfVIP

A Hierarchical Compositional System for Rapid Object Detection. Long Zhu Alan Yuille Department of Statistics Department of Statistics University of California at Los Angeles University of California at Los Angeles Los Angeles, CA 90095 Los Angeles, CA 90095 yuille@stat.ucla.edu In Advances in Neural Information Processing Systems 18. Cambridge, MA: MIT Press. A Bradford Book. Eds. Y. Weiss, B. Schoelkopf and J. Platt. Pages 1633-1640. May 2006. (Proceedings of NIPS 2005). 1 A Hierarchical Compositional System for Rapid Object Detection Long Zhu and Alan Yuille Department of Statistics University of California at Los Angeles Los Angeles, CA 90095 {lzhu,yuille}@stat.ucla.edu Abstract We describe a hierarchical compositional system for detecting de- formable objects in images. Objects are represented by graphical models. The algorithm uses a hierarchical tree where the root of the tree corre- sponds to the full object and lower-level elements of the tree correspond to simpler features. The algorithm proceeds by passing simple messages up and down the tree. The method works rapidly, in under a second, on 320 × 240 images. We demonstrate the approach on detecting cats, horses, and hands. The method works in the presence of background clutter and occlusions. Our approach is contrasted with more traditional