TY - JOUR U1 - Zeitschriftenartikel, wissenschaftlich - begutachtet (reviewed) A1 - Poschmann, Peter A1 - Huber, Patrik A1 - Rätsch, Matthias A1 - Kittler, Joseph A1 - Böhme, Hans-Joachim T1 - Fusion of tracking techniques to enhance adaptive real-time tracking of arbitrary objects JF - Procedia computer science N2 - In visual adaptive tracking, the tracker adapts to the target, background, and conditions of the image sequence. Each update introduces some error, so the tracker might drift away from the target over time. To increase the robustness against the drifting problem, we present three ideas on top of a particle filter framework: An optical-flow-based motion estimation, a learning strategy for preventing bad updates while staying adaptive, and a sliding window detector for failure detection and finding the best training examples. We experimentally evaluate the ideas using the BoBoT dataseta. The code of our tracker is available online. KW - adaptive tracking KW - particle filter KW - optical flow KW - sliding window Y1 - 2014 UN - https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-1015 U6 - https://doi.org/10.1016/j.procs.2014.11.025 DO - https://doi.org/10.1016/j.procs.2014.11.025 VL - 39 IS - 6th International conference on Intelligent Human Computer Interaction, IHCI 2014 SP - 162 EP - 165 S1 - 4 PB - Elsevier CY - Amsterdam ER -