Visual tracking based on adaptive interacting multiple model particle filter by fusing multiples cues

Article
  • 16 Downloads

Abstract

In visual tracking topic, developing a robust tracking method is very challenging, seen that there are many issues to look at, particularly, fast motion, target appearance changing, background clutter and camera motion. To override these problems, we present a new object tracking method with the fusion of interacting multiple models (IMM) and the particle filter (PF). First, the IMM is applied with a bank of parallel H∞ filter to estimate the global motion, the target motion is efficiently represented using only two parametric single models, and an adaptive strategy is preformed to adjust automatically the parameters of the two sub models at each recursive time step. Second, the particle filter is performed to estimate the local motion, we fuse the color and texture features to describe the appearance of the tracked object, we use the alpha Gaussian mixture model (α-GMM) to model the color feature distribution, the parameter α allows the probability function to possesses a flatter distribution, and the texture feature is represented by the distinctive uniform local binary pattern histogram (DULBP) based on the uniform local binary pattern (ULBP) operator; we fuse then the two features to represent the target’s appearance under the particle filter framework. We conduct quantitative and qualitative experiments on a variety of challenging public sequences; the results show that our method performs robustly and demonstrates strong accuracy.

Keywords

Visual tracking Particle filter Interactive multiple model Gaussien mixture model Expectation maximization 

References

  1. 1.
    Alahmadi A, Hussain M, Aboalsamh H, Muhammad G, Bebis G, Mathkour H (2017) Passive detection of image forgery using DCT and local binary pattern. SIViP 11:81–88CrossRefGoogle Scholar
  2. 2.
    Aristidou A, Lasenby J (2013) Real-time marker prediction and Cor-estimation in optical motion capture. Vis Comput 29:7–26CrossRefGoogle Scholar
  3. 3.
    M.S. Arulampalam , S. Maskell , N. Gordon , T. Clapp (2002) A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking, IEEE Transactions on Signal Processing 50(2):174–188.Google Scholar
  4. 4.
    Bar-Shalom Y, Li XR (1993) Estimation and tracking, principles, techniques and software. Artech House, BostonMATHGoogle Scholar
  5. 5.
    Bhattacharyya A (1943) On a measure of divergence between two statistical populations defined by their probability distributions. Bull Calcutta Math Soc 35(1):99–109MathSciNetMATHGoogle Scholar
  6. 6.
    Bhimani J, Yang Z, Leeser M (2017) Accelerating big data applications using lightweight virtualization framework on enterprise cloud. High Performance Extreme Computing Conference (HPEC), IEEEGoogle Scholar
  7. 7.
    Bhimani J, Mi N, Leeser M (2017) FIM: performance prediction for parallel computation in iterative data processing applications. Cloud Computing (CLOUD), 2017 I.E. 10th International Conference onGoogle Scholar
  8. 8.
    Cai Z, Gu Z, Yu ZL, Liu H, Zhang K (2016) A real-time visual object tracking system based on Kalman filter and MB-LBP feature matching. Multimedia Tools Appl 75(4):2393–2409CrossRefGoogle Scholar
  9. 9.
    Cui J, Member, IEEE, Liu Y, Xu Y, Zhao H, Zha H (2013)(IEEE Transactions on Systems, Man, and Cybernetics: Systems Tracking generic human motion via fusion of low- and high-dimensional approaches. IEEE Trans Syst Man Cybern Syst 43(4)Google Scholar
  10. 10.
    Dhassi Y, Aarab A, Alfidi M (2017) Robust visual tracking based on H∞ particle filter by adaptively integrating multiple cues. Int J Imaging Robot 17(1)Google Scholar
  11. 11.
    Dou J, Li J (2014) Robust visual tracking based on interactive multiple model particle filter by integrating multiple cues. Neurocomputing 135:118–129CrossRefGoogle Scholar
  12. 12.
    Fan Z, Ji H, Zhang Y (2015) Iterative particle filter (IPF) for visual tracking. Image Commun 36(C):140–153Google Scholar
  13. 13.
    Frank LL, Lihua X, Dan P (2007) Optimal and Robust Estimation. CRC Press, Boca RatonGoogle Scholar
  14. 14.
    Hu L, Li Z, Liu H (2015) Age group estimation on single face image using blocking ULBP and SVM. Chinese Intelligent Automation Conference, pp 431–438Google Scholar
  15. 15.
    Karasulu B, Korukoglu S (2011) A software for performance evaluation and comparison of people detection and tracking methods in video processing. Multimedia Tools Appl 55(3):677–723CrossRefGoogle Scholar
  16. 16.
    Karavasilis V, Nikou C, Likas A (2015) Visual tracking using spatially weighted likelihood of Gaussian mixture. Comput Vis Image Underst 140:43–57CrossRefGoogle Scholar
  17. 17.
    Kristan M (2008) Tracking people in video data using probabilistic models. Ph.D. dissertation, Faculty Elect. Eng., Univ. LjubljanaGoogle Scholar
  18. 18.
    Li P, Zhang T, Pece AEC (2003) Visual contour tracking based on particle filters. Image Vis Comput 21:111–123CrossRefGoogle Scholar
  19. 19.
    Liu Y, Zhang X, Cui J, Wu C, Aghajan H, Zha H (2010) Visual analysis of child-adult interactive behaviors in video sequences. 2010 I.E. 16th International Conference on Virtual Systems and Multimedia (VSMM)Google Scholar
  20. 20.
    Liu Y, Zhao H, Zha H (2012) Fusion of low-and high-dimensional approaches by trackers sampling for generic human motion tracking. 2012 21st International Conference on Pattern Recognition (ICPR)Google Scholar
  21. 21.
    Liu Y, Nie L, Han L, Zhang L, David S Rosenblum (2016) Action2activity: recognizing complex activities from sensor data. 2015 24th International Conference on Artificial Intelligence (IJCAI)Google Scholar
  22. 22.
    Liu L, Cheng L, Liu Y, Jia Y, Rosenblum DS (2016) Recognizing complex activities by a probabilistic interval-based model. 2016 30th National Conference on Artificial Intelligence (AAAI)Google Scholar
  23. 23.
    Liu Z, Song Y-q, Xie C-h, Tang Z (2016) A new clustering method of gene expression data based on multivariate Gaussian mixture models. SIViP 10(2):359–368CrossRefGoogle Scholar
  24. 24.
    Lu Y, Wei Y, Liu L, Zhong J, Sun L, Liu Y (2017) Towards unsupervised physical activity recognition using smartphone accelerometers. Multimedia Tools Appl 76(8):10701–10719CrossRefGoogle Scholar
  25. 25.
    Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measures with classification based on feature distributions. Pattern Recognition 29(1):51–59Google Scholar
  26. 26.
    Pan Z, Liu S, Fu W (2017) A review of visual moving target tracking. Multimedia Tools and Applications,Volume 76, Issue 16, pp 16989–17018.Google Scholar
  27. 27.
    Roemer J, Groman M, Yang Z (2015) Improving virtual machine migration via deduplication. 2014 I.E. 11th International Conference on Mobile Ad Hoc and Sensor SystemsGoogle Scholar
  28. 28.
    Rong Li X, Jilkov VP (2004) Survey of maneuvering target tracking. Part I. Dynamic models. IEEE Trans Aerosp Electron Syst 39:1333–1364CrossRefGoogle Scholar
  29. 29.
    Smeulders AWM, Chu DM, Cucchiara R (2014) Visual tracking: an experimental survey. IEEE Trans Pattern Anal Mach Intell 36(7):1442–1468.Google Scholar
  30. 30.
    Sobral A, Vacavant A (2014) A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Comput Vis Image Underst 14:4–21CrossRefGoogle Scholar
  31. 31.
    Sun W, Li X, Qiu J, Wang F (2014) Iterated unscented Kalman particle filter for visual tracking. J Comput Inf Syst 10(2):681–689Google Scholar
  32. 32.
    Sun X, Yao H, Lu X (2014) Dynamic multi-cue tracking using particle filter. SIViP 8:95–101CrossRefGoogle Scholar
  33. 33.
    Tamrakar D, Khanna P (2015) Occlusion invariant Palmprint recognition with ULBP histograms. Procedia Comput Sci 54:491–500CrossRefGoogle Scholar
  34. 34.
    Walia GS, Kapoor R (2016) Robust object tracking based upon adaptive multi-cue integration for video surveillance. Multimedia Tools Appl 75:15821–15847CrossRefGoogle Scholar
  35. 35.
    Wang X, Wang Y, Wan W, Hwang J-N (2014) Object tracking with sparse representation and annealed particle filter. SIViP 8:1059–1068CrossRefGoogle Scholar
  36. 36.
    Wang J, Wang T, Yang Z (2016) eSplash: efficient speculation in large scale heterogeneous computing systems. Performance Computing and Communications Conference (IPCCC), 2016 I.E. 35th International Conference onGoogle Scholar
  37. 37.
    Wang T, Wang J, Nguyen SN (2017) EA2S2: an efficient application-aware storage system for big data processing in heterogeneous clusters. Published in: Computer Communication and Networks (ICCCN), 2017 26th International Conference onGoogle Scholar
  38. 38.
    Wu D (2009) Parameter estimation for α-GMM based on maximum likelihood criterion. Neural Comput 21:1776–1795MathSciNetCrossRefMATHGoogle Scholar
  39. 39.
    Wu S, Hong L (2005) Hand tracking in a natural conversational environment by the interacting multiple model and probabilistic data association (IMM-PDA) algorithm. Pattern Recogn 38(11):2143–2158CrossRefGoogle Scholar
  40. 40.
    Xu Y, Dong J, Zhang B, Xu D (2016) Background modeling methods in video analysis: a review and comparative evaluation. CAAI Trans Intell Tech 1(1):43–60CrossRefGoogle Scholar
  41. 41.
    Xu Q, Wang Z, Wang F, Li J. (2018) Thermal comfort research on human CT data modeling. Multimedia Tools Appl 77(5):6311–6326.Google Scholar
  42. 42.
    Yang Z, Awasthi M, Ghosh M (2017) A fresh perspective on total cost of ownership models for flash storage in datacenters. Cloud Computing Technology and Science (CloudCom), 2016 I.E. International Conference onGoogle Scholar
  43. 43.
    Yang Z, Tai J, Bhimani J (2016) GREM. Dynamic SSD resource allocation in virtualized storage systems with heterogeneous IO workloads. Performance Computing and Communications Conference (IPCCC), 2016 I.E. 35th International Conference on.Google Scholar
  44. 44.
    Yin S, Na JH, Choi JY, Oh S (2011) Hierarchical Kalman-particle filter with adaptation to motion changes for object tracking. Comput Vis Image Underst 115:885–900CrossRefGoogle Scholar
  45. 45.
    Yu W, Gan L, Yang S, Ding Y, Jiang P, Wang J, Li S (2014) An improved LBP algorithm for texture and face classification. SIViP 8:155–161CrossRefGoogle Scholar
  46. 46.
    Zhao Z, Wang T, Liu F, Choe G, Yuan C, Cui Z (2017) Remarkable local resampling based on particle filter for visual tracking. Multimedia Tools Appl 76:835–860CrossRefGoogle Scholar
  47. 47.
    Zhou Z, Wu D, Zhu Z (2016) Object tracking based on Kalman particle filter with LSSVR. Int J Light Electron Optics 127(2):613–619CrossRefGoogle Scholar
  48. 48.
    Zhu H, Guo K, Chen S (2016) Fusion of Gaussian mixture models for maneuvering target tracking in the presence of unknown cross-correlation. Chin J Electron, Volume: 25, Issue: 2, Pages 270 - 276.Google Scholar

Copyright information

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

Authors and Affiliations

  1. 1.Laboratory of Electronics, Signals, Systems and Computers, Department Of Physics Faculty of Sciences Dhar- MahrazSidi Mohamed Ben Abdellah UniversityFesMorocco

Personalised recommendations