Adaptive visual tracking using the prioritized Q-learning algorithm: MDP-based parameter learning approach

Yilmaz, 2006, Object tracking: a survey, ACM Comput. Surv., 38, 10.1145/1177352.1177355 Leibe, 2008, Coupled object detection and tracking from static cameras and moving vehicles, IEEE Trans. Pattern Anal. Mach. Intell., 30, 1683, 10.1109/TPAMI.2008.170 Salti, 2012, Adaptive appearance modeling for video tracking: survey and evaluation, IEEE Trans. Image Process., 21, 4334, 10.1109/TIP.2012.2206035 Grabner, 2010, Tracking the invisible: learning where the object might be Yang, 2009, Context-aware visual tracking, IEEE Trans. Pattern Anal. Mach. Intell., 31, 1195, 10.1109/TPAMI.2008.146 Matthews, 2004, The template update problem, IEEE Trans. Pattern Anal. Mach. Intell., 26, 810, 10.1109/TPAMI.2004.16 Rahimi, 2008, Reducing drift in differential tracking, Comput. Vis. Image Underst., 109, 97, 10.1016/j.cviu.2006.12.004 Shi, 1994, Good features to track Ross, 2007, Incremental learning for robust visual tracking, Int. J. Comput. Vis., 77, 125 Jepson, 2003, Robust online appearance models for visual tracking, IEEE Trans. Pattern Anal. Mach. Intell., 25, 1296, 10.1109/TPAMI.2003.1233903 Kwon, 2009, Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo Sampling, 1208 Zhou, 2004, Visual tracking and recognition using appearance-adaptive models in particle filters, IEEE Trans. Image Process., 13, 1491, 10.1109/TIP.2004.836152 Collins, 2005, Online selection of discriminative tracking features, IEEE Trans. Pattern Anal. Mach. Intell., 27, 1631, 10.1109/TPAMI.2005.205 Avidan, 2007, Ensemble tracking, IEEE Trans. Pattern Anal. Mach. Intell., 29, 261, 10.1109/TPAMI.2007.35 Grabner, 2006, vol. 1, 260 Babenko, 2011, Robust object tracking with online multiple instance learning, IEEE Trans. Pattern Anal. Mach. Intell., 33, 1619, 10.1109/TPAMI.2010.226 Hare, 2011, STRUCK: structured output tracking with kernels, 263 Yang, 2009, Tracking nonstationary visual appearances by data-driven adaptation, IEEE Trans. Image Process., 18, 1633, 10.1109/TIP.2009.2019807 Grabner, 2008, Semi-supervised online boosting for robust tracking Tang, 2007, Co-tracking using semi-supervised support vector machines, 1 Kalal, 2009, Online learning of robust object detectors during unstable tracking Yang, 2009, Detection driven adaptive multi-cue integration for multiple human tracking, 1554 Yu, 2008, Online tracking and reacquisition using co-trained generative and discriminative trackers, 678 Kalal, 2012, Tracking-learning-detection, IEEE Trans. PAMI, 34, 1409, 10.1109/TPAMI.2011.239 Sutton, 1998 Barto, 1995, Learning to act using real-time dynamic programming, AIJ, 72, 81 Shani, 2005, An MDP-based recommender system, J. Mach. Learn. Res., 6, 1265 Bhanu, 2000, Adaptive integrated image segmentation and object recognition, IEEE Trans. Syst. Man Cybern. C Appl. Rev., 30, 427, 10.1109/5326.897070 Ross, 2008, Online planning algorithms for POMDPs, J. Artif. Intell. Res., 32, 663, 10.1613/jair.2567 Paquet, 2006, Hybrid POMDP algorithms Wang, 2012, A framework for moving target detection, recognition and tracking in UAV videos, 69 Watkins, 1989 Peng, 1998, Delayed reinforcement learning for adaptive image segmentation and feature extraction, IEEE Trans. Syst. Man Cybern. C Appl. Rev., 28, 482, 10.1109/5326.704593 Welch, 2006 Chen, 2010, Two-stage object tracking method based on kernel and active contour, IEEE Trans. Circ. Syst. Video Technol., 20, 605, 10.1109/TCSVT.2010.2041819 Czitrom, 1999, One-factor-at-a-time versus designed experiments, Am. Stat., 53, 2 Shen, 2013, Evolutionary adaptive eye tracking for low-cost human computer interaction applications, J. Electron. Imaging, 22, 10.1117/1.JEI.22.1.013031 Kaelbling, 1996, Reinforcement learning: a survey, J. Artif. Intell. Res., 4, 237, 10.1613/jair.301 Busoniu, 2008, A comprehensive survey of multi-agent reinforcement learning, IEEE Trans. Syst. Man Cybern. C. Appl. Rev., 38, 156, 10.1109/TSMCC.2007.913919 Stalder, 2009, Beyond semi-supervised tracking: tracking should be as simple as detection, but not simpler than recognition, 1409 Grabner, 2006, Real-time tracking via online boosting, 47 Adam, 2006, vol. 1, 798 Wu, 2013, Online object tracking: a benchmark, 2411 Zhang, 2012, Real-time compressive tracking Henriques, 2012, Exploiting the circulant structure of tracking-by-detection with kernels Carroll, 2002, vol. 10, 180