Advertisement

Deep Adaptive Update of Discriminant KCF for Visual Tracking

  • Xin Ning
  • Weijun Li
  • Weijuan Tian
  • Xuchi
  • Dongxiaoli
  • Zhangliping
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11306)

Abstract

In order to solve the challenges of In-plane/Out-of-plane Rotation (IPR/OPR), fast motion (FM) and occlusion (OCC), a new robust visual tracking framework combining an adaptive template update strategy and tracking validity evaluation, named (AU_DKCF) is presented in this paper. Specifically, the proposed appearance discriminant models are firstly used to determine the tracking validity, and then a new adaptive template update strategy is introduced, which provides an efficient update mechanism to distinguish IPR/OPR from FM and OCC states, and furthermore, a new visual tracking framework AU_DKCF is presented, which combines object detection to distinct FM and OCC states. We implement two versions of the proposed tracker with the representations from both conventional hand-crafted and deep convolution neural networks (CNNs) based features to validate the strong compatibility of the algorithm. Experiment results demonstrate the state-of-the-art performance in tracking accuracy and speed for processing the cases of IPR/OPR, FM and OCC.

Keywords

Visual tracking Kernelized correlation filters Discriminant model Convolution neural network Object detection 

Notes

Acknowledgements

This work was supported by the National Nature Science Foundation of China (No. 61572458).

References

  1. 1.
    Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. 38(4), 1–45 (2006)CrossRefGoogle Scholar
  2. 2.
    Cannons, K.: A review of visual tracking. Technical report CSE-2008-07, York University, Canada (2008)Google Scholar
  3. 3.
    Henriques, J.F., Caseiro, R., Martins, P., et al.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)CrossRefGoogle Scholar
  4. 4.
    Danelljan, F.M., Shahbaz, K., Felsberg, M., Van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR, pp. 1090–1097. IEEE (2014)Google Scholar
  5. 5.
    Jia, X., Lu, H., Yang, M.-H.: Visual tracking via adaptive structural local sparse appearance model. In: CVPR, pp. 1822–1829. IEEE (2012)Google Scholar
  6. 6.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409–1422 (2012)CrossRefGoogle Scholar
  7. 7.
    Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR, pp. 1269–1276. IEEE (2010)Google Scholar
  8. 8.
    Ross, D.A., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. Int. J. Comput. Vision 77(1–3), 125–141 (2008)CrossRefGoogle Scholar
  9. 9.
    Hong, S., You, T., Kwak, S., Han, B.: Online tracking by learning discriminative saliency map with convolutional neural network. In: Blei, D., Bach, F. (eds.) ICML, pp. 597–606 (2015)Google Scholar
  10. 10.
    Ma, C., Huang, J.-B., Yang, X., Yang, M.-H.: Hierarchical convolutional features for visual tracking. In: ICCV, pp. 3074–3082 (2015)Google Scholar
  11. 11.
    Qi, Y., et al.: Hedged deep tracking. In: CVPR, pp. 4303–4311. IEEE (2016)Google Scholar
  12. 12.
    Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: ICCV, pp. 3119–3127. IEEE (2015)Google Scholar
  13. 13.
    Wang, L., Ouyang, W., Wang, X., Lu, H.: STCT: sequentially training convolutional networks for visual tracking. In: CVPR (2016)Google Scholar
  14. 14.
    Hare, S., Saffari, A., Torr, P.H.: Struck: structured output tracking with kernels. In: ICCV, pp. 263–270. IEEE (2011)Google Scholar
  15. 15.
    Ning, J., Yang, J., Jiang, S., Zhang, L., Yang, M.-H.: Object tracking via dual linear structured SVM and explicit feature map. In: CVPR, pp. 4266–4274. IEEE (2016)Google Scholar
  16. 16.
    Wang, M., Liu, Y., Huang, Z.: Large margin object tracking with circulant feature maps. In: CVPR, Honolulu, HI, USA (2017)Google Scholar
  17. 17.
    Chan, T.H., Jia, K., Gao, S., et al.: PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR, pp. 2411–2418 (2013)Google Scholar
  19. 19.
    Hare, S., Saffari, A., Torr, P.: Struck Structured output tracking with kernels. In: ICCV (2011)Google Scholar
  20. 20.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning detection. In: TPAMI (2012)Google Scholar
  21. 21.
    Wu, Y., Shen, B., Ling, H.: Online robust image alignment via iterative convex optimization. In: CVPR (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Xin Ning
    • 1
    • 2
  • Weijun Li
    • 1
  • Weijuan Tian
    • 2
  • Xuchi
    • 2
  • Dongxiaoli
    • 1
    • 2
  • Zhangliping
    • 1
    • 2
  1. 1.Institute of SemiconductorsChinese Academy of SciencesBeijingChina
  2. 2.Cognitive Computing Technology Wave Joint LabBeijingChina

Personalised recommendations