Skip to main content
SpringerLink
Log in

Hierarchical convolutional features for visual tracking via two combined color spaces with SVM classifier

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

As the state-of-the-art object trackers majority, hierarchical convolutional features (HCF) cannot recover tracking processes from problems of drifting caused by several challenges, especially by heavy occlusion, scale variation, and illumination variation. In this paper, we present a new effective method with the aim of treating these challenges robustly based on two principal tasks. First, we infer the target location using multichannel correlation maps, resulting from the combination of five learned correlation filters with convolutional features. In order to handle the illumination variation and get more rich features, we exploit an HSV energy condition to control the use of two color spaces, RGB and HSV. Second, we use the histogram of gradient features to learn another correlation filter in order to estimate the scale variation. Furthermore, we exploit an online training SVM classifier for target re-detecting in failure cases. The extensive experiments on a commonly used tracking benchmark dataset justify that our tracker significantly improves HCF and outperforms the state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. (CSUR) 38(4), 13 (2006)

    Article  Google Scholar 

  2. Wu, D., Zou, W., Li, X., Zhao, Y.: Kernalised Multi-resolution Convnet for Visual Tracking (2017). arXiv preprint arXiv:1708.00577

  3. Mei, X., Ling, H.: Robust visual tracking using ℓ 1 minimization. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1436–1443. IEEE (2009, September)

  4. Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. Int. J. Comput. Vision 77(1), 125–141 (2008)

    Article  Google Scholar 

  5. Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: Robust visual tracking via multi-task sparse learning. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2042–2049. IEEE (2012, June)

  6. Babenko, B., Yang, M.H., Belongie, S.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1619–1632 (2011)

    Article  Google Scholar 

  7. Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409–1422 (2012)

    Article  Google Scholar 

  8. Zhang, J., Ma, S., Sclaroff, S.: MEEM: robust tracking via multiple experts using entropy minimization. In: European Conference on Computer Vision, pp. 188–203. Springer, Cham (2014, September)

  9. Hare, S., Saffari, A., Torr, P.H.: Struck: structured output tracking with kernels. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 263–270. IEEE (2011, November)

  10. Grabner, H., Leistner, C., Bischof, H.: Semi-supervised on-line boosting for robust tracking. In: Computer Vision-ECCV 2008, pp. 234–247 (2008)

  11. Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2544–2550. IEEE (2010, June)

  12. Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)

    Article  Google Scholar 

  13. Danelljan, M., Häger, G., Khan, F., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference, Nottingham, September 1–5, 2014. BMVA Press (2014)

  14. Li, Y., Zhu, J.: A scale adaptive kernel correlation filter tracker with feature integration. In: ECCV Workshops (2), pp. 254–265 (2014, September)

  15. Zhong, Z., Wang, M., Shi, Y., Gao, W.: A convolutional neural network-based flame detection method in video sequence, pp. 1–9. Signal, Image Video Process. (2018)

    Google Scholar 

  16. Chen, L., Fan, C., Yang, H., Hu, S., Zou, L., Deng, D.: Face age classification based on a deep hybrid model. Signal Image Video Process. 1–9 (2018)

  17. Protasov, S., Khan, A.M., Sozykin, K., Ahmad, M. Using deep features for video scene detection and annotation. Signal Image Video Process. 1–9 (2018)

  18. Jia, B., Feng, W., Zhu, M.: Obstacle detection in single images with deep neural networks. SIViP 10(6), 1033–1040 (2016)

    Article  Google Scholar 

  19. Revathi, A.R., Kumar, D.: An efficient system for anomaly detection using deep learning classifier. SIViP 11(2), 291–299 (2017)

    Article  Google Scholar 

  20. Fan, J., Xu, W., Wu, Y., Gong, Y.: Human tracking using convolutional neural networks. IEEE Trans. Neural Netw. 21(10), 1610–1623 (2010)

    Article  Google Scholar 

  21. Hong, S., You, T., Kwak, S., Han, B.: Online tracking by learning discriminative saliency map with convolutional neural network. In: International Conference on Machine Learning, pp. 597–606 (2015, June)

  22. Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411–2418 (2013)

  23. Ma, C., Huang, J.B., Yang, X., Yang, M.H.: Hierarchical convolutional features for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3074–3082 (2015)

  24. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint arXiv:1409.1556

  25. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005, Vol. 1, pp. 886–893. IEEE (2005, June)

  26. Li, Y., Zhang, Y., Xu, Y., Wang, J., Miao, Z.: Robust scale adaptive kernel correlation filter tracker with hierarchical convolutional features. IEEE Signal Process. Lett. 23(8), 1136–1140 (2016)

    Article  Google Scholar 

  27. Ma, C., Yang, X., Zhang, C., Yang, M. H.: Long-term correlation tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5388–5396 (2015)

  28. Huang, W., Gu, J., Ma, X., Li, Y.: Correlation filter-based self-paced object tracking. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4437–4442. IEEE (2017, May)

  29. Wibowo, S.A., Lee, H., Kim, E.K., Kim, S. Multi-scale color features based on correlation filter for visual tracking. In: 2017 International Conference on Signals and Systems (ICSigSys), pp. 272–277. IEEE (2017, May)

  30. Zhang, B., Li, Z., Cao, X., Ye, Q., Chen, C., Shen, L., Jill, R., et al.: Output constraint transfer for kernelized correlation filter in tracking. IEEE Trans. Syst. Man Cybern.: Syst. 47(4), 693–703 (2017)

    Article  Google Scholar 

  31. Wang, X., O’Brien, M., Xiang, C., Xu, B., Najjaran, H.: Real-time visual tracking via robust Kernelized Correlation Filter. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4443–4448. IEEE (2017, May)

  32. Gundogdu, E., Ozkan, H., Alatan, A.A.: Extending correlation filter-based visual tracking by tree-structured ensemble and spatial windowing. IEEE Trans. Image Process. 26(11), 5270–5283 (2017)

    Article  MathSciNet  Google Scholar 

  33. Ma, C., Xu, Y., Ni, B., Yang, X.: When correlation filters meet convolutional neural networks for visual tracking. IEEE Signal Process. Lett. 23(10), 1454–1458 (2016)

    Article  Google Scholar 

  34. Dollár, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532–1545 (2014)

    Article  Google Scholar 

  35. Touil, D.E., Terki, N., Medouakh, S.: Learning spatially correlation filters based on convolutional features via PSO algorithm and two combined color spaces for visual tracking. Appl. Intell. 1–10 (2017)

  36. Gao, J., Ling, H., Hu, W., Xing, J.: Transfer learning based visual tracking with gaussian processes regression. In: European Conference on Computer Vision, pp. 188–203. Springer, Cham (2014, September)

  37. Zhong, W., Lu, H., Yang, M.H.: Robust object tracking via sparse collaborative appearance model. IEEE Trans. Image Process. 23(5), 2356–2368 (2014)

    Article  MathSciNet  MATH  Google Scholar 

  38. Wang, N., Yeung, D.Y.: Learning a deep compact image representation for visual tracking. In: Advances in Neural Information Processing Systems, pp. 809–817 (2013)

  39. Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., Torr, P.H. Fully-convolutional siamese networks for object tracking. In: European Conference on Computer Vision, pp. 850–865. Springer, Cham (2016, October)

  40. Fan, H., Ling, H.: Parallel tracking and verifying: A framework for real-time and high accuracy visual tracking. In: Proceedings of IEEE International Conference on Computer Vision, Venice, Italy (2017, October)

  41. Huang, C., Lucey, S., Ramanan, D.: Learning policies for adaptive tracking with deep feature cascades. InL IEEE International Conference on Computer Vision (ICCV), pp. 105–114 (2017, October)

  42. He, A., Luo, C., Tian, X., Zeng, W.: A twofold siamese network for real-time object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4834–4843 (2018, February)

  43. Galoogahi, H.K., Fagg, A., Lucey, S.: Learning background-aware correlation filters for visual tracking. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 21–26 (2017, July)

  44. Wang, N., Zhou, W., Tian, Q., Hong, R., Wang, M., Li, H. Multi-Cue Correlation Filters for Robust Visual Tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4844–4853 (2018)

  45. Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Cehovin, L., Fernandez, G,, Vojir, T., Hager, et al.: The visual object tracking vot2016 challenge results. In: ECCV Workshop (2016)

  46. Danelljan, M., Robinson, A., Khan, F. S., Felsberg, M.: Beyond correlation filters: Learning continuous convolution operators for visual tracking. In: European Conference on Computer Vision, pp. 472–488. Springer, Cham (2016, October)

  47. Nam, H., Han, B. Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4293–4302 (2016)

  48. Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.: Staple: complementary learners for real-time tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1401–1409 (2016)

  49. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)

    Article  MathSciNet  Google Scholar 

  50. Nister, D., Stewenius, H. Scalable recognition with a vocabulary tree. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 2161–2168. IEEE (2006)

  51. Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for uav tracking. In: European Conference on Computer Vision, pp. 445–461. Springer, Cham (2016, October)

  52. Danelljan, M., Hager, G., Shahbaz Khan, F., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4310–4318 (2015)

Download references

Author information

Authors and Affiliations

  1. Energy Systems Modeling Laboratory, University of Biskra, Biskra, Algeria

    Djamel Eddine Touil & Saadia Medouakh

  2. Department of Electrical Engineering, University of Biskra, Biskra, Algeria

    Nadjiba Terki

Authors
  1. Djamel Eddine Touil
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nadjiba Terki
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Saadia Medouakh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Djamel Eddine Touil.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Touil, D.E., Terki, N. & Medouakh, S. Hierarchical convolutional features for visual tracking via two combined color spaces with SVM classifier. SIViP 13, 359–368 (2019). https://doi.org/10.1007/s11760-018-1364-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-018-1364-z

Keywords

Search

Navigation