Object Tracking Algorithm based on Improved Context Model in Combination with Detection Mechanism for Suspected Objects

  • Xiuyan TianEmail author
  • Haifang Li
  • Hongxia Deng


Built upon the methodology of “spatio-temporal context”, a simple yet robust object tracking method is proposed for solving the occlusion problems in this paper. This algorithm makes full use of the context information of the object and its local background to calculate the features, which maximumlly improve the occlusion predictive response and recapture accuracy. Firstly, an early warning mechanism is adopted to realize the occlusion detection. Once the object is fully occluded, the object position with accurate motion information saved in the early warning is predicted and memory tracking model is used to delete the suspected object region, which reduces the matching complexity. Finally, a confidence strategy for similarity measurement is adopted to capture the suspected object when the object appears, and the optimal confidence is introduced to get an adaptive update model. Many simulation experiments in benchmark videos show that our proposed algorithm achieves more favorable performance than these existing state-of-the-art algorithms.


Object tracking Occlusion detection Early warning Context information Confidence degree Spatio-temporal feature 



This work was supported by the National Natural Science Foundation of Shanxi Province (No.2014021022-5), and the Technological Project of State Grid Corporation of China (No.5205301500). The authors thank Zhang Kaihua and Kalal for providing their results.


  1. 1.
    Bay H, Tuytelaars T, Van Gool L, et al. (2006) SURF: speeded up robust features[C]. European Conference on Computer Vision, 404–417Google Scholar
  2. 2.
    Chen X, Davis J (2008) An occlusion metric for selecting robust camera configurations. machine vision applications 19. 4 217–222.Google Scholar
  3. 3.
    Cui J, Liu Y, Xu Y, Zhao H, Zha H (2013) Tracking generic human motion via fusion of low- and high-dimensional approaches. IEEE Trans Syst Man Cybern B 43(4):996–1002CrossRefGoogle Scholar
  4. 4.
    Henriques J, Caseiro R, Martins P, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with kernels. In: ECCV. pp. 702–715 16Google Scholar
  5. 5.
    Henriques JF, Caseiro R, Martins P et al (2015) High-Speed Tracking with Kernelized Correlation Filters[J]. IEEE Trans Pattern Anal Mach Intell 37(3):583–596CrossRefGoogle Scholar
  6. 6.
    Jiang H, Li J, Wang D et al. (2016) Multi-feature tracking via adaptive weights[J]. Neurocomputing, 189–201Google Scholar
  7. 7.
    Jun K, Min J, Xiao-Wei T, Yi-Ning S, Ke J, Guang-Rui W (2015) Target tracking by compressive sensing based on Gaussian differential graph[J]. J Infrared Millimeter Waves 34(1):100–105Google Scholar
  8. 8.
    Kalal, M, Matas, (2011) Tracking Learning Detection, Pattern Analysis and Machine IntelligenceGoogle Scholar
  9. 9.
    Kalal Z, Matas J, Mikolajczyk K (2010) Pn learning: Bootstrapping binary classifiers by structural constraints. In: CVPR. pp. 49–56Google Scholar
  10. 10.
    Liu, Ye et al. Fusion of low-and high-dimensional approaches by trackers sampling for generic human motion tracking. International Conference on Pattern Recognition IEEE, 2012:898–901Google Scholar
  11. 11.
    Liu Y et al. (2015) Action2Activity: recognizing complex activities from sensor data. International Conference on Artificial Intelligence AAAI Press, 1617–1623Google Scholar
  12. 12.
    Liu Y et al (2016) From action to activity: Sensor-based activity recognition. Neurocomputing 181:108–115CrossRefGoogle Scholar
  13. 13.
    Liu L, Cheng L, Liu Y et al. (2016) Recognizing Complex Activities by a Probabilistic Interval-Based Model[C]// Thirtieth AAAI Conference on Artificial Intelligence. AAAI Press, 1266–1272Google Scholar
  14. 14.
    Lowe DG (2004) Distinctive Image Features from Scale-Invariant Keypoints[J]. Int J Comput Vis 60(2):91–110MathSciNetCrossRefGoogle Scholar
  15. 15.
    Ross DA, Lim J, Lin R, et al. (2008) Incremental Learning for Robust Visual Tracking [J]. International Journal of Computer Vision, 125–141Google Scholar
  16. 16.
    Ross D, Lim J, Lin R, Yang MH (2008) Incremental learning for robust visual tracking. IJCV 77(1):125–141CrossRefGoogle Scholar
  17. 17.
    Su Z, Yuming Z, Liang H (2017) A multi-feature compressed target tracking algorithm based on redundant dictionary [J]. Acta Tribune of China 38(06):1140–1146Google Scholar
  18. 18.
    Tao XIE, Ensi WU (2017) A Robust Kernelized Correlation Tracking Algorithm for Infrared Targets Based on Ensemble Learning. JEIT 40(3):602–609Google Scholar
  19. 19.
    Torr HS (2011) Struck: Structured output tracking with kernels. In: ICCV. pp. 263–270Google Scholar
  20. 20.
    Valmadre J et al. (2017) End-to-End Representation Learning for Correlation Filter Based Tracking. computer vision and pattern recognition 5000–5008Google Scholar
  21. 21.
    Wen L, Cai Z, Lei Z, Yi D, Li S (2012) Online spatio-temporal structure context learning for visual tracking. In: ECCV. pp. 716–729Google Scholar
  22. 22.
    Wu Y et al. (2017) Nondestructive measurement of internal quality attributes of apple fruit by using NIR spectroscopy. Multimed Tools Appl 1–17Google Scholar
  23. 23.
    Yang C, Yu C, Yan M, Yuan X et al (2016) A Particle Filter Infrared Target Tracking Algorithm Based on Feature Fusion[J]. Inf Technol 38(03):211–217Google Scholar
  24. 24.
    Zhang KH, Song HH (2013) Real-time visual tracking Via online weighted multiple instance learning[J]. Pattern Recogn 46(1):397–411MathSciNetCrossRefGoogle Scholar
  25. 25.
    Zhang KH, Zhang L, Yang MH et al (2013) Robust object tracking via active feature selection[J]. IEEE Trans Circuits syst Video Technol 23(11):1957–1967CrossRefGoogle Scholar
  26. 26.
    Zhang KH, Zhang L, Yang MH (2013) Real-time object tracking via online discriminative feature selection[J]. IEEE Trans Image Process 22(12):4664–4677MathSciNetCrossRefGoogle Scholar
  27. 27.
    Zhang KH, Zhang L, Yank MH (2014) Fast compressive tracking[J]. IEEE Trans Pattern Anal Mach Intell 36(10):2002–2015CrossRefGoogle Scholar
  28. 28.
    Zhang KH, Zhang L, Liu Q S, et al. (2014) Fast visual tracking via dense spatio-temporal context learning[C]//European Conference on Computer Vision, 127–141Google Scholar
  29. 29.
    Zhang K, Zhang L, Yang M et al (2014) Fast Compressive Tracking.[J]. IEEE Trans Pattern Anal Mach Intell 36(10):2002–2015CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Information and ComputerTaiyuan University of TechnologyTaiyuanChina
  2. 2.Department of Economy & ManagementYuncheng UniversityYunchengChina

Personalised recommendations