cvpr cvpr2013 cvpr2013-414 cvpr2013-414-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Lu Zhang, Laurens van_der_Maaten
Abstract: Model-free trackers can track arbitrary objects based on a single (bounding-box) annotation of the object. Whilst the performance of model-free trackers has recently improved significantly, simultaneously tracking multiple objects with similar appearance remains very hard. In this paper, we propose a new multi-object model-free tracker (based on tracking-by-detection) that resolves this problem by incorporating spatial constraints between the objects. The spatial constraints are learned along with the object detectors using an online structured SVM algorithm. The experimental evaluation ofour structure-preserving object tracker (SPOT) reveals significant performance improvements in multi-object tracking. We also show that SPOT can improve the performance of single-object trackers by simultaneously tracking different parts of the object.
[1] A. Adam, E. Rivlin, and I. Shimshoni. Robust fragmentsbased tracking using the integral histogram. In CVPR, pages 798–805, 2006.
[2] B. Babenko, M.-H. Yang, and S. Belongie. Robust object tracking with online multiple instance learning. PAMI, 33(8): 1619–1632, 2011.
[3] S. Branson, P. Perona, and S. Belongie. Strong supervison from weak annotation: Interactive training of deformable part models. In ICCV, pages 1832–1839, 2011.
[4] M. Breitenstein, F. Reichlin, B. Leibe, E. Koller-Meier, and L. Van Gool. Online multiperson tracking-by-detection from a single, uncalibrated camera. PAMI, 33(9): 1820–1833, 2011.
[5] K. Crammer, O. Dekel, J. Keshet, S. Shalev-Shwartz, and Y. Singer. Online passive-aggressive algorithms. Journal of Machine Learning Research, 7(Mar):55 1–585, 2006.
[6] D. Cristinacce and T. F. Cootes. Automatic feature localisation with constrained local models. Pattern Recognition, 41(10):3054–3067, 2008.
[7] N. Dalal and B. Triggs. Histograms of oriented gradients for
[8]
[9]
[10]
[11]
[12]
[13]
[14]
[15]
[16]
[17] human detection. In CVPR, pages 886–893, 2005. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. PAMI, 32(9): 1627–1645, 2010. H. Grabner, M. Grabner, and H. Bischof. Real-time tracking via on-line boosting. In BMVC, pages 47–56, 2006. S. Hare, A. Saffari, and P. Torr. Struck: Structured output tracking with kernels. In ICCV, pages 263–270, 2011. M. Isard and J. Maccormick. Bramble: A Bayesian multiblob tracker. In CVPR, pages 34–41, 2001 . Z. Kalal, J. Matas, and K. Mikolajczyk. P-n learning: Bootstrapping binary classifiers by structural constraints. In CVPR, pages 49–56, 2010. J. Kwon and K. Lee. Visual tracking decomposition. In CVPR, pages 1269–1276, 2010. N. Lawrence. Probabilistic non-linear principal component analysis with Gaussian process latent variable models. Journal of Machine Learning Research, 6: 1783–18 16, 2005. V. Lepetit and P. Fua. Keypoint recognition using randomized trees. PAMI, 28(9): 1456–1479, 2006. X. Mei and H. Ling. Robust visual tracking and vehicle classification via sparse representation. PAMI, 33:2259–2272, 2011. T. Minka. Discriminative models, not discriminative training. Technical Report MSR-TR-2005-144, Microsoft Research, 2005. 111 888444224 Figure 2. Tracking results on seven of the twelve videos (David Indoor, Dollar, Girl, Tiger 2, Coke Can, Occl. Face 2, and Occl. Face) obtained by the MIL, OAB, TLD, and mst-SPOT trackers. Figure best viewed in color.
[18] S. Pellegrini, K. Ess, A.and Schindler, and L. van Gool. You’ll never walk alone: Modeling social behavior for multitarget tracking. In ICCV, pages 261–268, 2009.
[19] J. C. Platt. Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. Advances in Large Margin Classifiers, MIT Press, 1999.
[20] D. Ross, J. Lim, R.-S. Lin, and M.-H. Yuang. Incremental learning for robust visual tracking. IJCV, 77(1): 125–141, 2008.
[21] I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Al-
[22]
[23]
[24]
[25] tun. Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6: 1453–1484, 2005. P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In CVPR, pages 5 11–5 18, 2001 . Z. Wu, A. Thangali, S. Sclaroff, and M. Betke. Coupling detection and data association for multiple object tracking. In CVPR, pages 1948–1955, 2012. Z. Xiangxin and D. Ramanan. Face detection, pose estimation, and landmark localization in the wild. In CVPR, pages 2879–2886, 2012. T. Yu and Y. Wu. Decentralized multiple target tracking using netted collaborative autonomous trackers. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005. 111888444533