The Community for Technology Leaders
Green Image
Issue No. 12 - Dec. (2014 vol. 36)
ISSN: 0162-8828
pp: 2538-2551
Federico Pernici , Media Integration and Communication Center (MICC), University of Florence, Florence, Italy
Alberto Del Bimbo , Media Integration and Communication Center (MICC), University of Florence, Florence, Italy
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 along the object template. This allows taking into account the 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 occlusion. 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 drift in very long video sequences.
Context, Feature extraction, Shape, Search problems, Target tracking, Detectors, Visualization,Computer vision, Tracking, Motion, Invariants, Feature representation,template update, Visual real-time tracking, long-term tracking, learning from video, local feature invariance
Federico Pernici, Alberto Del Bimbo, "Object Tracking by Oversampling Local Features", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 36, no. , pp. 2538-2551, Dec. 2014, doi:10.1109/TPAMI.2013.250
425 ms
(Ver 3.3 (11022016))