Advertisement

The visual object tracking algorithm research based on adaptive combination kernel

  • Yuantao Chen
  • Jin Wang
  • Runlong Xia
  • Qian Zhang
  • Zhouhong Cao
  • Kai Yang
Original Research
  • 32 Downloads

Abstract

In order to enhance the robustness to complicated changes of multiple objects and complex background scene, the visual object tracking algorithm based on Adaptive Combination Kernel has been proposed in the paper. The object tracking procedure has been decomposed into two subtasks: Translation Filter and Scale Filter to estimate the object’s details. Firstly, the Translation Kernel Tracker has used the adaptive combination of Linear Kernel Filter and Gaussian Kernel Filter. The objective function has been developed to obtain the weight coefficients for Linear Kernel filter and the Gaussian Kernel filter, which incorporates not only empirical risk but also maximum value of response output for each kernel. The Adaptive Combination Kernel has the advantages of both local kernel and global kernel. Secondly, the tracking position has been calculated according to the response output of adaptive combination kernel correlation filter. Thirdly, according to the maximum response value, the scene-adaptive learning rate has been designed in the translation filter. The translation filter can be updated with the adaptive learning rate. Finally, one-dimensional scale filter has been used to estimate the object scale. The extensive experimental results have shown that the proposed algorithm is optimal on OTB-50 dataset in success rate and distance precision parameters, which is 6.8 percentage points and 4.1% points than those of KCF and is 2.0 percentage points and 3.2% points than those of BSET. The proposed algorithm has better robustness to the deformation and occlusion than others.

Keywords

Visual object tracking Gaussian kernel filter Kernel correlation filter Adaptive combination kernel Ridge regression 

Notes

Acknowledgements

This work is supported by the National Natural Science Foundation of China (nos. 61811530332, 6181101030, 61772454), the Open Research Fund of Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation (no. 2015TP1005), the Changsha Science and Technology Planning (nos. KQ1703018, KQ1706064), the Research Foundation of Education Bureau of Hunan Province (nos. 17A007, 16B009), the Teaching and Reforming Project of Changsha University of Science and Technology (nos. JG1755, JG1711, JG201815, XJT[2017]452 no. 132, XJT[2018]436 no. 193), the Major Project of Changsha Science and Technology Planning (no. KQ1703018-01), Changsha Industrial Science and Technology Commissioner (no. 2017-7). We are grateful to anonymous referees for useful comments and suggestions.

References

  1. An ZY, Guan H, Li JJ (2017) Robust visual tracking using the bidirectional scale estimation. Math Probl Eng 9:1–10Google Scholar
  2. Baker S, Matthews I (2004) Lucas-kanade 20 years on: a unifying framework. Int J Comput Vision 56(3):221–255CrossRefGoogle Scholar
  3. Bolme DS, Beveridge JR, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: Proceedings of the 2010 IEEE conference on computer vision and pattern recognition, IEEE Press, pp 2544–2550Google Scholar
  4. Chen YT, Xu WH, Kuang FJ, Gao SB (2013) The research and application of visual saliency and adaptive support vector machine in target tracking field. Comput Math Methods Med  https://doi.org/10.1155/2013/925341 zbMATHGoogle Scholar
  5. Chen YT, Xiong J, Xu WH, Zuo JW (2018) A novel online incremental and decremental learning algorithm based on variable support vector machine. Cluster Computing.  https://doi.org/10.1007/s10586-018-1772-4 Google Scholar
  6. Danelljan M, Khan FS, Felsberg M, Weijer JVD (2014) Adaptive color attributes for real-time visual tracking. In: Proceedings of the 2014 IEEE conference on computer vision and pattern recognition, IEEE Press, pp 1090–1097Google Scholar
  7. Danelljan M, Häger G, Khan FS, Felsberg M (2016) Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking. In: Proceedings of the 2016 IEEE conference on computer vision and recognition P, IEEE Press, pp 1430–1438Google Scholar
  8. Erfan BT, Ali ARH, Mehdi S, Arun KS, Jin W (2018) Semi-supervised learning with generative adversarial networks on digital signal modulation classification. Computers Mater Con 55(2):243–254Google Scholar
  9. Gong SR, Liu CP, Ji Y, Zhong BJ, Li YG, Dong HS (2019) Visual object tracking. In: Advanced image and video processing using MATLAB. Modeling and optimization in science and technologies,  https://doi.org/10.1007/978-3-319-77223-3_11
  10. Hare S, Saffari A, Torr PHS (2011) Struck: structured output tracking with kernels. In: Proceedings of the 2011 international conference on computer vision, IEEE Press, pp 263–270Google Scholar
  11. He SF, Lau RWH, Yang QX, Wang J, Yang MH (2017) Robust object tracking via locality sensitive histograms. IEEE Trans Circ Syst Video Technol 27(5):1006–1017CrossRefGoogle Scholar
  12. Henriques JF, Rui C, Martins P, Batista J (2015) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37(3):583–596CrossRefGoogle Scholar
  13. Hsia CH, Liou YJ, Chiang JS (2016) Directional prediction CamShift algorithm based on adaptive search pattern for moving object tracking. J Real-Time Image Proc 12(1):183–195CrossRefGoogle Scholar
  14. Jeong J, Yoon TS, Jin BP (2017) Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking. Expert Syst Appl 79:194–206CrossRefGoogle Scholar
  15. Kalal Z, Mikolajczyk K, Matas J (2012) Tracking-learning-detection. IEEE Trans Pattern Anal Mach Intell 34(7):1409–1422CrossRefGoogle Scholar
  16. Liu T, Wang G, Yang QX, Wang L (2016) Part-based tracking via discriminative correlation filters. IEEE Trans Circ Syst Video Technol 99:1–1CrossRefGoogle Scholar
  17. Liu J, Lin L, Cai ZH, Wang J, Hye-jin, Kim (2017) Deep web data extraction based on visual information processing. J Ambient Intell Humaniz Comput.  https://doi.org/10.1007/s12652-017-0587-0 Google Scholar
  18. Lukezic A, Vojir T, Zajc LC, Matas J, Kristan M (2017) Discriminative correlation filter with channel and spatial reliability. In: Proceedings of the 2017 IEEE computer vision and pattern recognition, IEEE Press, pp 4847–4856Google Scholar
  19. Ma C, Yang X, Zhang C (2015) Long-term correlation tracking. In: Proceedings of the 2015 IEEE conference on computer vision and recognition P, IEEE Press, pp 5388–5396Google Scholar
  20. Martin D, Gustav H, Fahad SK, Felsberg M (2016) Discriminative scale space tracking. IEEE Trans Pattern Anal Mach Intell 39(8):1561–1575Google Scholar
  21. Mazzeo PL, Spagnolo P, Leo M, Carcagnì P, Coco MD, Distante C (2017) Dense descriptor for visual tracking and robust update model strategy. J Ambient Intell Humaniz Comput.  https://doi.org/10.1007/s12652-017-0461-0 Google Scholar
  22. Mueller M, Smith N, Ghanem B (2017) Context-aware correlation filter tracking. In: Proceedings of the 2017 IEEE conference on computer vision and recognition P, IEEE Press, pp 1387–1395Google Scholar
  23. Oron S, Bar-Hillel A, Levi D, Avidan S (2012) Locally orderless tracking. In: Proceedings of the 2012 IEEE conference on computer vision and pattern recognition, IEEE Press, pp 1940–1947Google Scholar
  24. Sun L, Wang SF, Wang J, Zheng YH, Byeungwoo J (2017) Hyperspectral classification employing spatial-spectral low rank representation in hidden fields. J Ambient Intell Humaniz Comput.  https://doi.org/10.1007/s12652-017-0586-1 Google Scholar
  25. Thabet E, Khalid F, Sulaiman PS, Yaakob R (2018) Fast marching method and modified features fusion in enhanced dynamic hand gesture segmentation and detection method under complicated background. J Ambient Intell Humaniz Comput 9(3):755–769CrossRefGoogle Scholar
  26. Vojir T, Noskova J, Matas J (2014) Robust scale-adaptive mean-shift for tracking. Pattern Recogn Lett 49(3):250–258CrossRefGoogle Scholar
  27. Wang MM, Liu Y, Huang ZY (2017) Large margin object tracking with circulant feature maps. In: Proceedings of the 2017 IEEE Conference on computer vision and recognition P, IEEE Press, pp 4800–4808Google Scholar
  28. Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark. In: Proceedings of the 2013 IEEE conference on computer vision and pattern recognition, IEEE Press, pp 2411–2418Google Scholar
  29. Xiang LY, Li Y, Hao W, Yang P, Li F (2018) TUMK-ELM: a fast unsupervised heterogeneous data learning approach. IEEE Access 6:35305–35315CrossRefGoogle Scholar
  30. Yang LC, Jiang PL, Wang F, Wang X (2018) Robust real-time visual object tracking via multi-scale fully convolutional siamese networks. Multimedia Tools Appl 77(17):22131–22143CrossRefGoogle Scholar
  31. Zeng DJ, Dai Y, Li F, Simon Sherratt R, Wang J (2018) Adversarial learning for distant supervised relation extraction. Computers Mater Con 55(1):121–136Google Scholar
  32. Zhang KH, Zhang L, Yang MH, Zhang D (2014a) Fast tracking via spatio-temporal context learning. In: Proceedings of the 2014 European conference on computer vision, Springer, pp 398–403Google Scholar
  33. Zhang KH, Zhang L, Yang MH (2014b) Fast compressive tracking. IEEE Trans Pattern Anal Mach Intell 36(10):2002–2015CrossRefGoogle Scholar
  34. Zhang KH, Liu QS, Wu Y, Yang MH (2016) Robust visual tracking via convolutional networks without training. IEEE Trans Image Process 25(4):1779–1792MathSciNetGoogle Scholar
  35. Zhang L, Varadarajan J, Suganthan PN, Ahuja N, Moulin P (2017) Robust visual tracking using oblique random forests. In: Proceedings of the 2017 IEEE conference on computer vision and recognition P, IEEE Press, pp 5825–5834Google Scholar
  36. Zhang JM, Jin XK, Sun J, Wang J, Sangaiah AK (2018) Spatial and semantic convolutional features for robust visual object tracking. Multimedia Tools Appl.  https://doi.org/10.1007/s11042-018-6562-8 Google Scholar
  37. Zhao ZQ, Wang TJ, Liu F, Choe G, Yuan C (2017) Remarkable local resampling based on particle filter for visual tracking. Multimedia Tools Appl 76(1):835–860CrossRefGoogle Scholar
  38. Zhou XZ, Xie L, Zhang P, Zhang YN (2017) Online object tracking based on BLSTM-RNN with contextual-sequential labeling. J Ambient Intell Humaniz Comput 8(6):861–870CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation and School of Computer and Communicational EngineeringChangsha University of Science and TechnologyChangshaChina
  2. 2.Hunan Institute of Scientific and Technical InformationChangshaChina
  3. 3.Technical Quality DepartmentHunan ZOOMLION Intelligent Technology Company LimitedChangshaChina
  4. 4.School of Hydraulic EngineeringChangsha University of Science and TechnologyChangshaChina

Personalised recommendations