Abstract
Correlation filter-based trackers (CFTs) with multiple features have recently achieved competitive performance. However, such conventional CFTs simply combine these features via a fixed weight. Likewise, these trackers also utilize a fixed learning rate to update their models, which makes CFTs easily drift especially when the target suffers heavy occlusions. To tackle these issues, we propose a dynamic decision fusion strategy to automatically learn the weight from the corresponding response map, and accordingly, models are adaptively updated based on a reliability metric. Moreover, a novel kernelized scale estimation scheme is proposed by exploiting the nonlinear relationship over targets of different sizes. Qualitative and quantitative comparisons on the benchmark have demonstrated that the proposed approach significantly outperforms other state-of-the-art trackers.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust L1 tracker using accelerated proximal gradient approach. In: Computer Vision and Pattern Recognition (CVPR), pp. 1830–1837 (2012)
Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.: Staple: complementary learners for real-time tracking. In: Computer Vision and Pattern Recognition (CVPR), pp. 1401–1409 (2016)
Bibby, C., Reid, I.: Robust real-time visual tracking using pixel-wise posteriors. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 831–844. Springer, Heidelberg (2008). doi:10.1007/978-3-540-88688-4_61
Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: Computer Vision and Pattern Recognition (CVPR), pp. 2544–2550 (2010)
Cai, B., Xu, X., Xing, X., Jia, K.: BIT: biologically inspired tracker. Trans. Image Process. (TIP) 25(3), 1327–1339 (2016)
Chen, Z., Hong, Z., Tao, D.: An experimental survey on correlation filter-based tracking. Comput. Sci. 53(6025), 68–83 (2015)
Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference (BMVC), pp. 65.1–65.11 (2014)
Danelljan, M., Khan, F.S., Felsberg, M., Weijer, J.V.D.: Adaptive color attributes for real-time visual tracking. In: Computer Vision and Pattern Recognition (CVPR), pp. 1090–1097 (2014)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. Trans. Pattern Anal. Mach. Intell. (TPAMI) 32(9), 1627–1645 (2010)
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 702–715. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33765-9_50
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. Trans. Pattern Anal. Mach. Intell. (TPAMI) 37(3), 583–596 (2015)
Li, Y., Zhu, J., Hoi, S.C.H.: Reliable patch trackers: robust visual tracking by exploiting reliable patches. In: Computer Vision and Pattern Recognition (CVPR), pp. 353–361 (2015)
Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT press, Cambridge (2002)
Wang, N., Wang, J., Yeung, D.Y.: Online robust non-negative dictionary learning for visual tracking. In: International Conference on Computer Vision (ICCV), pp. 657–664 (2013)
Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: Computer Vision and Pattern Recognition (CVPR), pp. 2411–2418 (2013)
Zhang, K., Liu, Q., Wu, Y., Yang, M.H.: Robust visual tracking via convolutional networks without training. Trans. Image Process. (TIP) 25(4), 1779 (2016)
Zhang, T., Liu, S., Ahuja, N., Yang, M.H., Ghanem, B.: Robust visual tracking via consistent low-rank sparse learning. Int. J. Comput. Vis. (IJCV) 111(2), 171–190 (2015)
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China under Grant 61572315, Grant 6151101179, in part by 863 Plan of China under Grant 2015AA042308.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Peng, C., Liu, F., Yang, H., Yang, J., Kasabov, N. (2017). Correlation Filters with Adaptive Memories and Fusion for Visual Tracking. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10636. Springer, Cham. https://doi.org/10.1007/978-3-319-70090-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-70090-8_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70089-2
Online ISBN: 978-3-319-70090-8
eBook Packages: Computer ScienceComputer Science (R0)