Advertisement

Applied Intelligence

, Volume 49, Issue 11, pp 3864–3880 | Cite as

Research on scale adaptive particle filter tracker with feature integration

  • Yuqi XiaoEmail author
  • Difu Pan
Article
  • 89 Downloads

Abstract

This research proposes an improved particle filter tracking algorithm based on SGA (the adaptive genetic algorithm supervised by population convergence). In order to improve the robustness and efficiency of the particle filter tracker in various tracking scenarios, this study proposes an adaptive feature selection strategy based on Harris corner detection, SIFT features and colour features. In addition, the tracking frame scale of the traditional target tracking algorithm is fixed in the tracking process, which leads to many problems such as more invalid features and lower positioning accuracy. To solve these problems, this study proposes an adaptive tracking frame scale adjustment model based on the spatial position of particles. Furthermore, considering that the scale adaptive model cannot accurately reflect the target rotation deformation, this paper proposes an adaptive tracking frame scale and direction adjustment model based on the covariance descriptors to accurately track the rotation of the target and further reduce the invalid features of the rectangle frame. The extensive empirical evaluations on the benchmark dataset (OTB2015) and VOT2016 dataset demonstrate that the proposed method is very promising for the various challenging scenarios.

Keywords

Computer vision technology Particle filter Target tracking Fusion feature 

Notes

References

  1. 1.
    Danelljan M, Bhat G, Khan FS, et al (2017) ECO: Efficient Convolution Operators for Tracking,. 2017 IEEE Conference on Computer Vision and Pattern RecognitionGoogle Scholar
  2. 2.
    Fujita H, Cimr D (2019) Computer aided detection for fibrillations and flutters using deep convolutional neural network. Inf Sci 486:231–239CrossRefGoogle Scholar
  3. 3.
    Chongsheng Z, Changchang L, Xiangliang Z, George A (2017) An up-to-date comparison of state-of-the-art classification algorithms. Expert Syst Appl 82:128–150CrossRefGoogle Scholar
  4. 4.
    Gonczarek A, Tomczak JM (2016) Articulated tracking with manifold regularized particle filter. Springer-Verlag New York, Inc.Google Scholar
  5. 5.
    An X, Kim J, Han Y (2014) Optimal colour-based mean shift algorithm for tracking objects. IET Comput Vis 8(3):235–244CrossRefGoogle Scholar
  6. 6.
    Zhou Z, Zhou M, Shi X (2016) Target tracking based on foreground probability. Multimed Tools Appl 75(6):3145–3160CrossRefGoogle Scholar
  7. 7.
    Zhang X, Peng J, Yu W, Lin KC (2012) Confidence-level-based new adaptive particle filter for nonlinear object tracking. Int J Adv Robot Syst 9(1)Google Scholar
  8. 8.
    Li T, Sun S, Sattar TP, Corchado JM (2013) Fight sample degeneracy and impoverishment in particle filters: a review of intelligent approaches. Expert Syst Appl 41(8):3944–3954CrossRefGoogle Scholar
  9. 9.
    Lin SD, Lin JJ, Chuang CY (2015) Particle filter with occlusion handling for visual tracking. Image Processing IET 9(11):959–968MathSciNetCrossRefGoogle Scholar
  10. 10.
    Chen P, Qian H, Wang W, Zhu M (2011) Contour tracking using Gaussian particle filter. IET Image Process 5(5):440–447CrossRefGoogle Scholar
  11. 11.
    Rymut B, Kwolek B, Krzeszowski T (2013) GPU-accelerated human motion tracking using particle filter combined with PSO. In: International Conference on Advanced Concepts for Intelligent Vision Systems. Springer-Verlag, New York, pp 426–437CrossRefGoogle Scholar
  12. 12.
    Yang J et al (2015) Fast Object Tracking Employing Labelled Particle Filter for Thermal Infrared Imager. International Journal of Distributed Sensor Networks 2015:2Google Scholar
  13. 13.
    Wei Q, Dai T, Ma T, Liu Y, Gu Y (2016) Crystal identification in dual-layer-offset doi-pet detectors using stratified peak tracking based on svd and mean-shift algorithm. IEEE Trans Nucl Sci 63(5):2502–2508CrossRefGoogle Scholar
  14. 14.
    Wang X et al (2010) Annealed particle filter based on particle swarm optimization for articulated three-dimensional human motion tracking. Opt Eng 49(1)Google Scholar
  15. 15.
    Dai CH, Zhu YF, Chen WR (2006) Adaptive probabilities of crossover and mutation in genetic algorithms based on cloud model. Information Theory Workshop, 2006. ITW '06 Chengdu. IEEE 24:710–713Google Scholar
  16. 16.
    Hong TP, Wang HS, Lin WY, Lee WY (2002) Evolution of appropriate crossover and mutation operators in a genetic process. Appl Intell 16(1):7–17CrossRefGoogle Scholar
  17. 17.
    Mallah R, Quintero A, Farooq B (2017) Distributed classification of urban congestion using VANET. IEEE Trans Intell Transp Syst 18(9):2435–2442CrossRefGoogle Scholar
  18. 18.
    Azab MM, Shedeed HA, Hussein AS (2014) New technique for online object tracking-by-detection in video. IET Image Process 8(12):794–803CrossRefGoogle Scholar
  19. 19.
    Tanzmeister G, Wollherr D (2017) Evidential grid-based tracking and mapping. IEEE Trans Intell Transp Syst 18(6):1454–1467Google Scholar
  20. 20.
    Shmaliy YS (2012) Suboptimal FIR filtering of nonlinear models in additive white Gaussian noise. IEEE Trans Signal Process 60(10):5519–5527MathSciNetCrossRefGoogle Scholar
  21. 21.
    Ning J, Zhang L, Zhang D, Wu C (2010) Robust mean-shift tracking with corrected background-weighted histogram. IET Comput Vis 6(1):62–69MathSciNetCrossRefGoogle Scholar
  22. 22.
    Sun J (2010) Object tracking using an adaptive Kalman filter combined with mean shift. Opt Eng 49(2):020503-1–020503-3CrossRefGoogle Scholar
  23. 23.
    Lowe DG (1999) Object Recognition from Local Scale-Invariant Features. ICCV IEEE Computer Society 2:1150Google Scholar
  24. 24.
    Danelljan M, Robinson A., Khan FS, Felsberg M (2016) Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking,” European Conference on Computer Vision. Springer, Cham. 472-488Google Scholar
  25. 25.
    Danelljan M, Häger G, Khan FS, Felsberg M (2016) Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking. Computer Vision and Pattern Recognition. IEEE:1430–1438Google Scholar
  26. 26.
    Hong Z, Chen Z, Wang C et al (2015) MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking. Computer Vision and Pattern Recognition. IEEE:749–758Google Scholar
  27. 27.
    Galoogahi HK, Fagg A, Lucey S (2017) Learning Background-Aware Correlation Filters for Visual Tracking. IEEE Computer Society:1144–1152Google Scholar
  28. 28.
    Wang M, Liu Y, Huang Z (2017) Large Margin Object Tracking with Circulant Feature Maps. IEEE Computer Society:4800–4808Google Scholar
  29. 29.
    Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr P (2015) Staple: complementary learners for real-time tracking. Proc IEEE Conf Comput Vis Pattern Recognit 38(2):1401–1409Google Scholar
  30. 30.
    Li Y, Zhu J (2014) A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration. ECCV WorkshopsGoogle Scholar
  31. 31.
    Danelljan M, Häger G, Khan FS, Felsberg M (2014) Accurate Scale Estimation for Robust Visual Tracking. British Machine Vision Conference:65.1–65.11Google Scholar
  32. 32.
    Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark. Proc IEEE Computer Vision and Pattern Recognition 9:2411–2418Google Scholar
  33. 33.
    Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Čehovin L et al (2016) The visual object tracking vot2016 challenge results. In: ECCV workshopGoogle Scholar
  34. 34.
    Nam H, Baek M, Han B (2016) Modeling and propagating CNNS in a tree structure for visual tracking. arXiv preprint arXiv:1608.07242Google Scholar

Copyright information

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

Authors and Affiliations

  1. 1.School of Traffic and Transportation EngineeringCentral South UniversityChangshaChina
  2. 2.CRRC Zhuzhou Locomotive Co. Ltd.ZhuzhouChina

Personalised recommendations