Visual Tracking via Adaptive Tracker Selection with Multiple Features
Abstract
In this paper, a robust visual tracking method is proposed to track an object in dynamic conditions that include motion blur, illumination changes, pose variations, and occlusions. To cope with these challenges, multiple trackers with different feature descriptors are utilized, and each of which shows different level of robustness to certain changes in an object’s appearance. To fuse these independent trackers, we propose two configurations, tracker selection and interaction. The tracker interaction is achieved based on a transition probability matrix (TPM) in a probabilistic manner. The tracker selection extracts one tracking result from among multiple tracker outputs by choosing the tracker that has the highest tracker probability. According to various changes in an object’s appearance, the TPM and tracker probability are updated in a recursive Bayesian form by evaluating each tracker’s reliability, which is measured by a robust tracker likelihood function (TLF). When the tracking in each frame is completed, the estimated object’s state is obtained and fed into the reference update via the proposed learning strategy, which retains the robustness and adaptability of the TLF and multiple trackers. The experimental results demonstrate that our proposed method is robust in various benchmark scenarios.
Keywords
Visual tracking multiple features transition probability matrix robust likelihood function tracker interaction appearance learningReferences
- 1.Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. IJCV 29(1), 5–28 (1998)CrossRefGoogle Scholar
- 2.Jilkov, V.P., Li, X.R.: Online Bayesian estimation of transition probabilities for markovian jump systems. IEEE Transactions on Signal Processing 52(6), 307–315 (2004)MathSciNetCrossRefGoogle Scholar
- 3.Ross, D., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. IJCV 77, 125–141 (2008)CrossRefGoogle Scholar
- 4.Santner, J., Leistner, C., Saffari, A., Pock, T., Bischof, H.: Prost: Parallel robust online simple tracking. In: CVPR, pp. 723–730 (2010)Google Scholar
- 5.Spengler, M., Schiele, B.: Towards robust multi-cue integration for visual tracking. Machine Vision and Applications 14(1), 50–58 (2003)CrossRefGoogle Scholar
- 6.Giebel, J., Gavrila, D.M., Schnörr, C.: A Bayesian Framework for Multi-cue 3D Object Tracking. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 241–252. Springer, Heidelberg (2004)CrossRefGoogle Scholar
- 7.Brasnett, P., Mihaylova, L., Canagarajah, N., Mihaylova, L., Canagarajah, N., Bull, D.: Particle filtering with multiple cues For object tracking. In: Proc. of SPIE’s Annual Symp. EI ST, pp. 430–441 (2005)Google Scholar
- 8.Wang, H., Suter, D.: Efficient visual tracking by probabilistic fusion of multiple cues. In: International Conference on Pattern Recognition, pp. 892–895 (2006)Google Scholar
- 9.Leichter, I., Lindenbaum, M., Rivlin, E.: A general framework for combining visual trackers - the ”black boxes” approach. IJCV 67(3), 343–363 (2006)CrossRefGoogle Scholar
- 10.Badrinarayanan, V., Perez, P., Clerc, F.L., Oisel, L.: Probabilistic color and adaptive multi-feature tracking with dynamically switched priority between cues. In: ICCV, pp. 1–8 (2007)Google Scholar
- 11.Du, W., Piater, J.: A Probabilistic Approach to Integrating Multiple Cues in Visual Tracking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 225–238. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 12.Moreno-Noguer, F., Sanfeliu, A., Samaras, D.: Dependent multiple cue integration for robust tracking. PAMI 30(4), 670–685 (2008)CrossRefGoogle Scholar
- 13.Stenger, B., Woodley, T., Cipolla, R.: Learning to track with multiple observers. In: CVPR, pp. 2647–2654 (2009)Google Scholar
- 14.Zelniker, E.E., Hospedales, T.M., Gong, S., Xiang, T.: A unified Bayesian framework for adaptive visual tracking. In: BMVC, pp. 18.1–18.11 (2009)Google Scholar
- 15.Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR, pp. 1269–1276 (2010)Google Scholar
- 16.Mei, X., Ling, H.: Robust visual tracking using l1 minimization. In: ICCV, pp. 1436–1443 (2009)Google Scholar
- 17.Bar-Shalom, Y., Li, X.R., Kirubarajan, T.: Estimation with applications to tracking and navigation. Wiley, New York (2001)CrossRefGoogle Scholar
- 18.Mei, X., Ling, H., Wu, Y., Blasch, E., Bai, L.: Minimum error bounded efficient l1 tracker with occlusion detection. In: CVPR, pp. 1257–1264 (2011)Google Scholar
- 19.Kim, S.-J., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: An interior-point method for large-scale l1 regularized least squares. IEEE Journal on Selected Topics in Signal Processing 1(4), 606–617 (2007)CrossRefGoogle Scholar
- 20.Yang, M.-H.: Face detection. In: Encyclopedia of Biometrics, pp. 303–308 (2009)Google Scholar
- 21.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
- 22.Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Computing Surveys 38(4) (2006)Google Scholar
- 23.Cifuentes, C.G., Sturzel, M., Jurie, F., Brostow, G.J.: Motion models that only work sometimes. In: BMVC (2012)Google Scholar
- 24.Everingham, M., Van Gool, L.J., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV 88(2), 303–338 (2010)CrossRefGoogle Scholar
- 25.Doucet, A., Godsill, S., Andrieu, C.: On sequential Monte Carlo sampling methods for Bayesian filtering. Statistics and Computing 10(3), 197–208 (2000)CrossRefGoogle Scholar
- 26.Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: CVPR, pp. 798–805 (2006)Google Scholar
- 27.Babenko, B., Yang, M.-H., Belongie, S.: Visual tracking with online multiple instance learning. In: CVPR, pp. 983–990 (2009)Google Scholar
- 28.Kalal, Z., Matas, J., Mikolajczyk, K.: P-n learning: bootstrapping binary classifiers by structural constraints. In: CVPR, pp. 49–56 (2010)Google Scholar