Beyond semi-supervised tracking: Tracking should be as simple as detection, but not simpler than recognition

We present a multiple classifier system for model-free tracking. The tasks of detection (finding the object of interest), recognition (distinguishing similar objects in a scene), and tracking (retrieving the object to be tracked) are split into separate classifiers in the spirit of simplifying each classification task. The supervised and semi-supervised classifiers are carefully trained on-line in order to increase adaptivity while limiting accumulation of errors, i.e. drifting. In the experiments, we demonstrate real-time tracking on several challenging sequences, including multi-object tracking of faces, humans, and other objects. We outperform other on-line tracking methods especially in case of occlusions and presence of similar objects.

[1]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[2]  Luc Van Gool,et al.  Exploring context to learn scene specific object detectors , 2009 .

[3]  Robert D. Nowak,et al.  Unlabeled data: Now it helps, now it doesn't , 2008, NIPS.

[4]  Shai Avidan,et al.  Support Vector Tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, CVPR.

[6]  Maria-Florina Balcan,et al.  Co-Training and Expansion: Towards Bridging Theory and Practice , 2004, NIPS.

[7]  Takahiro Ishikawa,et al.  The template update problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[9]  Vladimir Pavlovic,et al.  Face tracking and recognition with visual constraints in real-world videos , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Horst Bischof,et al.  Classifier grids for robust adaptive object detection , 2009, CVPR.

[11]  Horst Bischof,et al.  Semi-supervised On-Line Boosting for Robust Tracking , 2008, ECCV.

[12]  Horst Bischof,et al.  On-line Boosting and Vision , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[13]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Qi Zhao,et al.  Co-Tracking Using Semi-Supervised Support Vector Machines , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[15]  Horst Bischof,et al.  Learning Features for Tracking , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Horst Bischof,et al.  Real-Time Tracking via On-line Boosting , 2006, BMVC.

[17]  Yanxi Liu,et al.  Online Selection of Discriminative Tracking Features , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[19]  Sergio A. Velastin,et al.  How close are we to solving the problem of automated visual surveillance? , 2008, Machine Vision and Applications.

[20]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[21]  Vincent Lepetit,et al.  Randomized trees for real-time keypoint recognition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[22]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[23]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[24]  Gérard G. Medioni,et al.  Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers , 2008, ECCV.