Abstract
Tracking objects in the presence of clutter and occlusion remains a challenging problem. Current approaches often rely on a priori target dynamics and/or use nearly rigid image context to determine the target position. In this paper, a novel algorithm is proposed to estimate the location of a target while it is hidden due to occlusion. The main idea behind the algorithm is to use contextual dynamical cues from multiple supporter features which may move with the target, move independently of the target, or remain stationary. These dynamical cues are learned directly from the data without making prior assumptions about the motions of the target and/or the support features. As illustrated through several experiments, the proposed algorithm outperforms state of the art approaches under long occlusions and severe camera motion.
Chapter PDF
Similar content being viewed by others
References
Ding, T., Sznaier, M., Camps, O.: Receding horizon rank minimization based estimation with applications to visual tracking. In: CDC, pp. 3446–3451 (2008) 2, 4, 7, 10, 12
Yang, M., Wu, Y., Hua, G.: Context-aware visual tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence 31, 1195–1209 (2009) 2, 3, 4, 10
Grabner, H., Matas, J., Van Gool, L., Cattin, P.: Tracking the invisible: Learning where the object might be. In: CVPR, pp. 1285–1292 (2010) 2, 3, 4, 10, 12
Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: CVPR (2008) 1
Breitenstein, M., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L.: Robust tracking-by-detection using a detector confidence particle filter. In: ICCV (2009) 1
Dinh, T.B., Vo, N., Medioni, G.: Context tracker: Exploring supporters and distracters in unconstrained environments. In: CVPR (2011) 1
Beymer, D., Konolige, K.: Real-time tracking of multiple people using continuous detection. In: ICCV (1999) 1
Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. IJCV 29, 5–28 (1998) 1
Julier, S., Uhlmann, J., Durrant-Whyte, H.: A new approach for filtering nonlinear systems. In: ACC, vol. 3, pp. 1628–1632 (1995) 1
North, B., Blake, A., Isard, M., Rittscher, J.: Learning and classification of complex dynamics. IEEE Trans. PAMI 22 (2000) 1
Ayazoglu, M., Li, B., Dicle, C., Sznaier, M., Camps, O.: Dynamic subspace-based coordinated multicamera tracking. In: ICCV (2011) 2, 4, 5
Cerman, L., Matas, J., Hlaváč, V.: Sputnik Tracker: Having a Companion Improves Robustness of the Tracker. In: Salberg, A.-B., Hardeberg, J.Y., Jenssen, R. (eds.) SCIA 2009. LNCS, vol. 5575, pp. 291–300. Springer, Heidelberg (2009) 2
Ho, B., Kalman, R.: Effective construction of linear, state-variable models from input/output functions. Regelungstechnik 14, 545–548 (1966) 5
Moonen, M., Moor, B.D., Vandenberghe, L., Vandewalle, J.: On- and off-line identification of linear state space models. Int. J. of Control 49, 219–232 (1989) 5
Fazel, M., Hindi, H., Boyd, S.: A rank minimization heuristic with application to minimum order system approximation. In: ACC, vol. 6, pp. 4734–4739 (2001) 8
Fazel, M., Hindi, H., Boyd, S.: Log-det heuristic for matrix rank minimization with applications to hankel and euclidean distance matrices. In: ACC, vol. 3, pp. 2156–2162 (2003) 8
Lowe, D.: Object recognition from local scale-invariant features. In: ICCV (1999) 9
Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008) 9, http://www.vlfeat.org/
Lublinerman, R., Sznaier, M., Camps, O.: Dynamics based robust motion segmentation. In: CVPR, vol. 1, pp. 1176–1184 (2006) 10
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xiong, F., Camps, O.I., Sznaier, M. (2012). Dynamic Context for Tracking behind Occlusions. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7576. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33715-4_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-33715-4_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33714-7
Online ISBN: 978-3-642-33715-4
eBook Packages: Computer ScienceComputer Science (R0)