Federico Pernici , University of Florence, Florence
Alberto Del Bimbo , University of Florence, Florence
In this paper, we present the ALIEN tracking method that exploits oversampling of local invariant representations to build a robust object/context discriminative classifier. To this end, we use multiple instances of scale invariant local features weakly aligned to the object template. This allows to take account of 3D shape deviations from planarity and their interactions with shadows, occlusions and sensor quantization for which no invariant representations can be defined. A non parametric learning algorithm based on the transitive matching property discriminates the object from the context and prevents improper object template updating during occlusions. We show that our learning rule has asymptotic stability under mild conditions and confirms the drift-free capability of the method in long term tracking. A real-time implementation of the ALIEN tracker has been evaluated in comparison with the state of the art tracking systems on an extensive set of publicly available video sequences that represent most of the critical conditions occurring in real tracking environments. We have reported superior or equal performance in most of the cases and verified tracking with no drifting in very long video sequences.
Computer vision, Tracking, Motion, Invariants, Feature representation
F. Pernici and A. Del Bimbo, "Object Tracking by Oversampling Local Features," in IEEE Transactions on Pattern Analysis & Machine Intelligence.