Multimedia Tools and Applications

, Volume 50, Issue 1, pp 49–73 | Cite as

Dynamic tracking re-adjustment: a method for automatic tracking recovery in complex visual environments

  • Anastasios Doulamis


Detection and analysis of events from video sequences is probably one of the most important research issues in computer vision and pattern analysis society. Before, however, applying methods and tools for analyzing actions, behavior or events, we need to implement robust and reliable tracking algorithms able to automatically monitor the movements of many objects in the scene regardless of the complexity of the background, existence of occlusions and illumination changes. Despite the recent research efforts in the field of object tracking, the main limitation of most of the existing algorithms is that they are not enriched with automatic recovery strategies able to re-initialize tracking whenever its performance severely deteriorates. This is addressed in this paper by proposing an automatic tracking recovery tool which improves the performance of any tracking algorithm whenever the results are not acceptable. For the recovery, non-linear object modeling tools are used which probabilistically label image regions to object classes. The models are also time varying. The first property is implemented in our case using concepts from functional analysis which allow parametrization of any arbitrary non-linear function (with some restrictions on its continuity) as a finite series of known functional components but of unknown coefficients. The second property is addressed by proposing an innovative algorithm that optimally estimates the non-linear model at an upcoming time instance based on the current non-linear models that have been already approximated. The architecture is enhanced by a decision mechanism which permits verification of the time instances in which tracking recovery should take place. Experimental results on a set of different video sequences that present complex visual phenomena (full and partial occlusions, illumination variations, complex background, etc) are depicted to demonstrate the efficiency of the proposed scheme in proving tracking in very difficult visual content conditions. Additionally, criteria are proposed to objectively evaluate the tracking performance and compare it with other strategies.


Tracking recovery Object detection Event analysis 



This work is supported by the European Union funded project SCOVIS “Self Configurable Cognitive Video Supervsion” supported by the Seventh Framework Programme (FP7/2007–2013) under grant agreement no 216465.


  1. 1.
    Arulampalam S, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for on-line non-linear/non-Gaussian Bayesian tracking. IEEE Trans Signal Process 50(2):174–188CrossRefGoogle Scholar
  2. 2.
    Chen D, Yang J (2007) Robust object tracking via online dynamic spatial bias appearance models. IEEE Trans Pattern Anal Mach Intell 29(12):2157–2169CrossRefGoogle Scholar
  3. 3.
    Comanicu D, Ramesh V, Meer P (2000) Real-time tracking of non-rigid objects using mean shift. Proc Int’l Conf Computer Vision and Pattern Recognition, pp 142-149Google Scholar
  4. 4.
    Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control, Signal Syst 2:303–314MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Davatzikos C, Prince J, Bryan R (1996) Image registration based on boundary mapping. IEEE Trans Med Imag 15(1):112–115CrossRefGoogle Scholar
  6. 6.
    Doucet A, Godsill S, Andrieu C (2000) On sequential Monte Carlo sampling methods for Bayesian filtering. Stat Comput 10(3):197–208CrossRefGoogle Scholar
  7. 7.
    Doulamis A, Doulamis N, Ntalianis K, Kollias S (2003) An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture. IEEE Trans Neural Netw 14(3):616–630CrossRefGoogle Scholar
  8. 8.
    Doulamis A, Kosmopoulos D, Christogiannis C, Varvarigou D (2004) Polymnia: personalised leisure and entertainment over cross media intelligent platforms. European Workshop on Integration of Knowledge, Semantics and Digital Media Technology, London, UK, 25–26 November 2004Google Scholar
  9. 9.
    Doulamis A,van Gool L, Nixon M, Varvarigou T, Doulamis N (2008) First ACM international workshop on analysis and retrieval of events, actions and workflows in video streams. 16th ACM International Conference on Multimedia, Vancouver, Canada, October 2008Google Scholar
  10. 10.
    Doulamis A, Kosmopoulos D, Sardis E, Varvarigou T (2008) An architecture for a self configurable video supervision. ACM Workshop on Analysis and Retrieval of Events, Actions and Workflows in Video Streams, Vancouver, Canada, October 2008Google Scholar
  11. 11.
    Grimson W.E.L, Stauffer C (1999) Adaptive background mixture models for real-time tracking. Proc Int’l Conf Computer Vision and Pattern Recognition, pp 22–29Google Scholar
  12. 12.
    Heisele B, Kressel U, Ritter W (1997) Tracking non-rigid, moving objects based on color cluster flow. Proc Int’l Conf Computer Vision and Pattern Recognition, pp 253–257Google Scholar
  13. 13.
    Isard M, Blake A (1998) Condensation c conditional density propagation for visual tracking. Int J Comput Vis 29(1):5–28CrossRefGoogle Scholar
  14. 14.
    Jeyakar J, Venkatesh Babu R, Ramakrishnan KR (2008) Robust object tracking with background-weighted local Kernels. Comput Vis Image Underst 112:296–309CrossRefGoogle Scholar
  15. 15.
    Jodoin P-M, Mignotte M, Konrad J (2007) Statistical background subtraction using spatial cues. IEEE Trans Circuits Syst Video Technol 17(12):1758–1763CrossRefGoogle Scholar
  16. 16.
    Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331CrossRefGoogle Scholar
  17. 17.
    Kreyszig E (1989) Introductory functional analysis with applications. Wiley, New YorkMATHGoogle Scholar
  18. 18.
    Leibe B, Schindler K, Cornelis N, Van Gool L (2008) Coupled object detection and tracking from static cameras and moving vehicles. IEEE Trans Pattern Anal Mach Intell 30(10):1683–1698CrossRefGoogle Scholar
  19. 19.
    Leichter I, Lindenbaum M, Rivlin E (2009) Tracking by Affine Kernel transformations using color and boundary cues. IEEE Trans Pattern Anal Mach Intell 31(1):164–171CrossRefGoogle Scholar
  20. 20.
    Lucas B, Kanade T (1981) An iterative image registration technique with an application to stereo vision. Proc DARPA Image Understanding Workshop, pp 121–130Google Scholar
  21. 21.
    Medeiros H, Park J, Kak A (2008) Distributed object tracking using a cluster-based Kalman filter in wireless camera networks. IEEE J Sel Topics Signal Process 2(4):448–463CrossRefGoogle Scholar
  22. 22.
    Nascimento JC, Marques JS (2006) Performance evaluation of object detection algorithms for video surveillance. IEEE Trans Multimedia 8(4):761–774CrossRefGoogle Scholar
  23. 23.
    Odobez J-M, Gatica-Perez D, Ba SO (2006) Embedding motion in model-based stochastic tracking. IEEE Trans Image Process 15(11):3515–3531CrossRefGoogle Scholar
  24. 24.
    Rasmussen C, Hager GD (2001) Probabilistic data association methods for tracking complex visual objects. IEEE Trans Pattern Anal Mach Intell 23(6):560–576CrossRefGoogle Scholar
  25. 25.
    Shahrokni A, Drummond T, Fua P (2004) Texture boundary detection for real-time tracking. Proc European Conf Computer Vision, pp 566–577Google Scholar
  26. 26.
    Shi J, Tomasi C (1994) Good features to track. Proc Int’l Conf Computer Vision and Pattern Recognition, pp 593–600Google Scholar
  27. 27.
    Smith GJD (2004) Behind the Screens: examining constructions of deviance and informal practices among CCTV control room operators in the UK. Surveill Soc 2(2/3):376–395Google Scholar
  28. 28.
    Stenger B, Ramesh V, Paragios N, Coetzee F, Bouhman J (2002) Topology free hidden markov models: application to background modeling. Proc Int’l Conf Computer Vision, pp 294–301Google Scholar
  29. 29.
    Tekalp M (1995) Digital video processing. Prentice Hall PTR, ISBN 0131900757Google Scholar
  30. 30.
    Tsai D-M, Lai S-C (2008) Independent component analysis-based background subtraction for indoor surveillance. IEEE Trans Image Process 18(1):158–167CrossRefGoogle Scholar
  31. 31.
    Wang D (1998) Unsupervised video segmentation based on watersheds and temporal tracking. IEEE Trans Circuits Syst Video Technol 8(5):539–546CrossRefGoogle Scholar
  32. 32.
    Wang P, Ji Q (2005) Multi-view face tracking with factorial and switching HMM. Seventh IEEE Workshops on Application of Computer Vision, 2005. WACV/MOTIONS 1:401–406Google Scholar
  33. 33.
    Wang H, Suter D, Schindler K, Shen C (2007) Adaptive object tracking based on an effective appearance filter. IEEE Trans Pattern Anal Mach Intell 29(9):1661–1667CrossRefGoogle Scholar
  34. 34.
    Yang J, Waibel A (1996) A real-time face tracker. Proc Workshop Computer Vision, pp 142–147Google Scholar
  35. 35.
    Yilmaz A, Li X, Shah B (2004) Contour based object tracking with occlusion handling in video acquired using mobile cameras. IEEE Trans Pattern Anal Mach Intell 26(11):1531–1536CrossRefGoogle Scholar
  36. 36.
    Yonemoto S, Sato M (2008) Multitarget Tracking Using Mean-shift with Particle Filter based Initialization. IEEE 12th International Conference Information Visualization, pp. 521–526Google Scholar
  37. 37.
    Zhong Y, Jain AK, Dubuisson-Jolly M-P (2000) Object tracking using deformable templates. IEEE Trans Pattern Anal Mach Intell 22(5):544–549CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Technical University of CreteChaniaGreece

Personalised recommendations