Advertisement

Scale-adaptive tracking based on perceptual hash and correlation filter

  • Wei Huang
  • Lingpeng LinEmail author
  • Tianqiang Huang
  • Jing Lin
  • Xueli Zhang
Article
  • 20 Downloads

Abstract

In the research on computer vision, object tracking has encountered various challenges, such as occlusion and scale variation. In recent years, tracking-by-detection methods have performed competitively. Some of these methods have focused on solving the problem of scale variation. Regardless, these algorithms perform poorly in real time. Recently, correlation filters have been widely used in object tracking because of their high efficiency; however, conventional correlation filter-based trackers cannot handle scale variation. Most correlation filter-based trackers update the template for each frame, and tracking offsets occur when a tracking error is present. To overcome these problems, we propose a novel scale-adaptive tracking algorithm that uses perceptual hash and correlation filter on the basis of tracking-by-detection methods. We employ kernel ridge regression to minimize the mean square error between the training image and the regression object, and construct a robust filter template to track the target center location. By tracking the 4 sub-blocks of the target image, the length and width expansion coefficients are calculated separately to update the target scale. We finally use the adaptive update strategy based on perceptual hash to effectively prevent the tracking offset caused by the template update error. Owing to the insensitivity to the scale variation and high efficiency of the perceptual hash, tracking becomes more robust in real time. Both quantitative and qualitative evaluations on Object Tracking Benchmark (OTB) indicate that the proposed tracking method performs more favorably compared with other state-of-the-art methods.

Keywords

Visual tracking Correlation filter Scale-adaptive Perceptual hash 

Notes

Acknowledgements

This study was supported by National Natural Science Foundation of China (No.61070062, No.61502103), Industry-University Cooperation Major Projects in Fujian Province (No.2015H6007), Science and Technology Program of Fujian (No.2014-G-76), Program for New Century Excellent Talents in University in Fujian Province (No. JAI1038), Science and Technology Department of Fujian Province K-Class Foundation Project (No.2011007) and Education Department of Fujian Province A-Class Foundation Project (No.JA10064).

Author contributions

Proposed the idea of the work: L. Lin, W. Huang, T. Huang; Conceived and designed the experiments: L. Lin, W. Huang, J. Lin; Performed the experiments: L. Lin, W. Huang, T. Huang, X. Zhang; Analyzed data: T. Huang, X. Zhang, J. Lin; Wrote and edited manuscript: L. Lin, W. Huang.

Compliance with ethical standards

Competing interests

The authors declare that they have no competing interests.

References

  1. 1.
    Avidan S (2001) Support vector tracking. In: Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on. 181: I-184–I-191Google Scholar
  2. 2.
    Avidan S (2007) Ensemble tracking. IEEE Trans Pattern Anal Mach Intell 29:261–271CrossRefGoogle Scholar
  3. 3.
    Babenko B, Yang MH, Belongie S (2009) Visual tracking with online multiple instance learning. In: Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. 983–990Google Scholar
  4. 4.
    Babenko B, Yang MH, Belongie S (2011) Robust object tracking with online multiple instance learning. IEEE Trans Pattern Anal Mach Intell 33:1619–1632CrossRefGoogle Scholar
  5. 5.
    Belagiannis V, Schubert F, Navab N, Ilic S (2012) Segmentation based particle filtering for real-time 2D object tracking. 842–855 (Springer Berlin Heidelberg)Google Scholar
  6. 6.
    Bolme DS, Beveridge JR, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: Computer Vision and Pattern Recognition. 2544–2550Google Scholar
  7. 7.
    Chen Z, Hong Z, Tao D (2014) An experimental survey on correlation filter-based tracking. Comput Sci 53:68–83Google Scholar
  8. 8.
    Choi J et al (2017) Attentional correlation filter network for adaptive visual tracking. In: IEEE Conference on Computer Vision and Pattern RecognitionGoogle Scholar
  9. 9.
    Comaniciu D, Ramesh V, Meer P (2002) Real-time tracking of non-rigid objects using mean shift. In: Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on. 2142Google Scholar
  10. 10.
    Danelljan M, Häger G, Khan FS, Felsberg M (2014) Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference. 65.61–65.11Google Scholar
  11. 11.
    Danelljan M, Khan FS, Felsberg M, Weijer JVD (2014) Adaptive color attributes for real-time visual tracking. In: Computer Vision and Pattern Recognition. 1090–1097Google Scholar
  12. 12.
    Everingham M, Gool LV, Williams CKI, Winn J, Zisserman A (2010) The Pascal visual object classes (VOC) challenge. Int J Comput Vis 88:303–338CrossRefGoogle Scholar
  13. 13.
    Grabner H, Leistner C, Bischof H (2008) Semi-supervised on-line boosting for robust tracking. In: European Conference on Computer Vision. 234–247Google Scholar
  14. 14.
    Hare S et al (2016) Struck: structured output tracking with kernels. IEEE Trans Pattern Anal Mach Intell 38:2096–2109CrossRefGoogle Scholar
  15. 15.
    Henriques JF, Caseiro R, Martins P, Batista J (2015) High-speed tracking with Kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37:583–596CrossRefGoogle Scholar
  16. 16.
    Hong Z, Chen Z, Wang C, Mei X (2015) Multi-store tracker (MUSTer): a cognitive psychology inspired approach to object tracking. Computer Vision and Pattern Recognition IEEE. 749–758Google Scholar
  17. 17.
    Ji H, Ling H, Wu Y, Bao C (2012) Real time robust L1 tracker using accelerated proximal gradient approach. In: Computer Vision and Pattern Recognition. 1830–1837Google Scholar
  18. 18.
    Jia X, Lu H, Yang MH (2012) Visual tracking via adaptive structural local sparse appearance model. In: Computer Vision and Pattern Recognition. 1822–1829Google Scholar
  19. 19.
    Kalal Z, Matas J, Mikolajczyk K (2014) P-N learning: bootstrapping binary classifiers by structural constraints. In: Computer Vision and Pattern Recognition. 49–56Google Scholar
  20. 20.
    Kulikowsk C (2011) Robust tracking using local sparse appearance model and K-selection. In: IEEE Conference on Computer Vision and Pattern Recognition. 1313–1320Google Scholar
  21. 21.
    Kwak S, Nam W, Han B, Han JH (2011) Learning occlusion with likelihoods for visual tracking. In: International Conference on Computer Vision. 1551–1558Google Scholar
  22. 22.
    Kwon J, Lee KM (2011) Tracking by sampling trackers. In: International Conference on Computer Vision. 1195–1202Google Scholar
  23. 23.
    Lee DY, Sim JY, Kim CS (2014) Visual tracking using pertinent patch selection and masking. In: Computer Vision and Pattern Recognition. 3486–3493Google Scholar
  24. 24.
    Li SZ, Jain A (2009) Hamming distance in Encyclopedia of biometrics (Springer US)Google Scholar
  25. 25.
    Li Y, Zhu J (2014) A scale adaptive kernel correlation filter tracker with feature integration. In: European Conference on Computer Vision. 254–265Google Scholar
  26. 26.
    Li X et al (2008) Visual tracking via incremental Log-Euclidean Riemannian subspace learning. In: Computer Vision and Pattern Recognition IEEE. 1–8Google Scholar
  27. 27.
    Li Y, Zhu J, Hoi SCH (2015) Reliable patch trackers: robust visual tracking by exploiting reliable patches. In: Computer Vision and Pattern Recognition. 353–361Google Scholar
  28. 28.
    Liu T, Wang G, Yang Q (2015) Real-time part-based visual tracking via adaptive correlation filters. In: Computer Vision and Pattern Recognition.4902–4912Google Scholar
  29. 29.
    Liu T, Wang G, Wang L, Chan KL (2015) Visual tracking via temporally smooth sparse coding. IEEE Signal Proc Lett 22:1452–1456CrossRefGoogle Scholar
  30. 30.
    Lucey S (2008) Enforcing non-positive weights for stable support vector tracking. In: Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. 1–8Google Scholar
  31. 31.
    Ma C, Yang X, Zhang C, Yang MH (2015) Long-term correlation tracking. In: IEEE Conference on Computer Vision and Pattern Recognition. 5388–5396Google Scholar
  32. 32.
    Mueller M, Smith N, Ghanem B (2017) Context-aware correlation filter tracking. In: Conference on Computer Vision and Pattern RecognitionGoogle Scholar
  33. 33.
    Ning J, Zhang L, Zhang D, Wu C (2012) Scale and orientation adaptive mean shift tracking. IET Comput Vis 6:52–61MathSciNetCrossRefGoogle Scholar
  34. 34.
    Niu XM, Jiao YH (2008) Overview of perceptual hashing. Acta Electron Sin 36:1405–1411Google Scholar
  35. 35.
    Rifkin R, Yeo G, Poggio T (2007) Regularized least-squares classification. Acta Electron Sin 190:93–104Google Scholar
  36. 36.
    Rodriguez A, Boddeti VN, Kumar BV, Mahalanobis A (2013) Maximum margin correlation filter: a new approach for localization and classification. IEEE Trans Image Proc A Publ IEEE Sign Proc Soc 22:631–643MathSciNetCrossRefGoogle Scholar
  37. 37.
    Ronghong C, Qingsong (2014) Research on recognition technology of 2-dimensional barcode. Appl Mech Mater 539:146–150CrossRefGoogle Scholar
  38. 38.
    Ross DA, Lim J, Lin RS, Yang MH (2008) Incremental learning for robust visual tracking. Int J Comput Vis 77:125–141CrossRefGoogle Scholar
  39. 39.
    Rui C, Martins P, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with kernels. In: European Conference on Computer Vision. 702–715Google Scholar
  40. 40.
    Saffari A, Leistner C, Santner J, Godec M (2009) On-line random forests. In: IEEE International Conference on Computer Vision Workshops. 1393–1400Google Scholar
  41. 41.
    Sevilla-Lara L (2012) Distribution fields for tracking. In: Computer Vision and Pattern Recognition. 1910–1917Google Scholar
  42. 42.
    Vojir T, Noskova J, Matas J (2013) Robust scale-adaptive mean-shift for tracking. In: Scandinavian Conference on Image Analysis. 652–663Google Scholar
  43. 43.
    Wang Q, Yang MH (2012) Online discriminative object tracking with local sparse representation. In: IEEE Workshop on the Applications of Computer Vision. 425–432Google Scholar
  44. 44.
    Wang X, Hua G, Han TX (2010) Discriminative tracking by metric learning. In: Computer Vision - ECCV 2010, European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings. 200–214Google Scholar
  45. 45.
    Wang N, Shi J, Yeung DY, Jia J (2015) Understanding and diagnosing visual tracking systems. In: Proceedings of the IEEE International Conference on Computer Vision. 3101–3109Google Scholar
  46. 46.
    Wang G, Wang G, Shuai B, Zhao L, Yang Q (2015) Exemplar based deep discriminative and shareable feature learning for scene image classification. Pattern Recogn 48:3004–3015CrossRefGoogle Scholar
  47. 47.
    Wang S, Wang D, Lu H (2017) Tracking with static and dynamic structured correlation filters. IEEE Trans Circ Syst Video Technol PP:1–1Google Scholar
  48. 48.
    Weijer JVD, Schmid C, Verbeek J, Larlus D (2009) Learning color names for real-world applications. IEEE Trans Image Proc A Publ IEEE Sign Proc Soc 18:1512–1523MathSciNetCrossRefGoogle Scholar
  49. 49.
    Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition. 2411–2418Google Scholar
  50. 50.
    Wu Y, Lim J, Yang MH (2015) Object tracking benchmark. IEEE Trans Pattern Anal Mach Intell 37:1834–1848CrossRefGoogle Scholar
  51. 51.
    Xiao Z, Lu H, Wang D (2014) L2-RLS-based object tracking. IEEE Trans Circ Syst Video Technol 24:1301–1309CrossRefGoogle Scholar
  52. 52.
    Xing J, Gao J, Li B, Hu W, Yan S (2014) Robust object tracking with online multi-lifespan dictionary learning. In: IEEE International Conference on Computer Vision. 665–672Google Scholar
  53. 53.
    Zhang YJ (2008) Image processing and analysis technology. 4–6 (Higher Education Press)Google Scholar
  54. 54.
    Zhang W, Kong X, You X (2007) Secure and robust image perceptual hashing. J Southeast Univ 37:189–192Google Scholar
  55. 55.
    Zhang K, Zhang L, Yang MH (2012) Real-time compressive tracking. In: European Conference on Computer Vision. 864–877Google Scholar
  56. 56.
    Zhang J, Ma S, Sclaroff S (2014) MEEM: robust tracking via multiple experts using entropy minimization. 188-203 (Springer International Publishing)Google Scholar
  57. 57.
    Zhang K, Zhang L, Liu Q, Zhang D, Yang MH (2014) Fast visual tracking via dense Spatio-temporal context learning. In: European Conference on Computer Vision. 127–141Google Scholar
  58. 58.
    Zhu G, Porikli F, Ming Y, Li H (2015) Lie-struck: affine tracking on lie groups using structured SVM. In: IEEE Winter Conference on Applications of Computer Vision, pp 63–70Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Mathematics and InformaticsFujian Normal UniversityFuzhouChina
  2. 2.Fujian Engineering Research Center of Public Service Big Data Mining and ApplicationFuzhouChina
  3. 3.Department of Computer ScienceFuzhou PolytechnicFuzhouChina

Personalised recommendations