Novel Adaptive Background Segmentation Algorithm for Multiple Object Tracking

  • Authors

    • V Ramalakshmi Kanthimathi
    • M Germanus Alex
    2018-08-15
    https://doi.org/10.14419/ijet.v7i3.27.17984
  • object tracking, background subtraction, scene detection
  • Multiple object tracking plays a vital role in many applications. The objective of this paper is to track multiple objects in all the scenes of the video sequence. In this paper, an algorithm is proposed to identify objects between scenes by dividing the scenes in the video sequence. Within each scene, objects are identified and tracked between scenes by segmenting the background adaptively. The proposed method is tested on four publicly available datasets. The experimental results substantially proved that the proposed method achieves better performance than other recent methods.

     

  • References

    1. [1] Black J, Ellis T & Rosin P, “Multi-View Image Surveillance and Trackingâ€, IEEE Workshop on Motion and Video Computing, (2002).

      [2] Wu B & Nevatia R, “Tracking of Multiple, Partially Occluded Humans Based on Static Body Part Detectionâ€, Conference on Computer Vision and Pattern Recognition, (2006), pp.951–958.

      [3] Vermaak J, Doucet A & Perez P, “Maintaining Multimodality Through Mixture Trackingâ€, International Conference on Computer Vision, (2003), pp.1110–1116.

      [4] Okuma K, Taleghani A, de Freitas N, Little J & Lowe D, “A Boosted Particle Filter: Multi target Detection and Trackingâ€, European Conference on Computer Vision, (2004).

      [5] Du W & Piater J, “Multi-Camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integrationâ€, Asian Conference on Computer Vision, (2007), pp.365–374.

      [6] Yu Q, Medioni G & Cohen I, “Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Associationâ€, International Conference on Computer Vision, (2007).

      [7] Maggio E, Taj M & Cavallaro A, “Efficient Multi-Target Visual Tracking Using Random Finite Setsâ€, IEEE Transactions On Circuits And Systems For Video Technology, Vol.18, No.8, (2008), pp.1016–1027.

      [8] Huang C, Wu B & Nevatia R, “Robust Object Tracking by Hierarchical Association of Detection Responsesâ€, European Conference on Computer Vision, (2008), pp.788–801.

      [9] Li Y, Huang C & Nevatia R, “Learning to Associate: Hybrid boosted Multi-Target Tracker for Crowded Sceneâ€, conference on Computer Vision and Pattern Recognition, (2009).

      [10] Beleznai C, Fruhstuck B & Bischof H, “Multiple Object Tracking Using Local Pcaâ€, International Conference on Image Processing, (2006).

      [11] Ge W & Collins RT, “Multi-target data association by tracklets with unsupervised parameter estimationâ€, British Machine Vision Conference, (2008).

      [12] Eshel R & Moses Y, “Homography Based Multiple Camera Detection and Tracking of People in a Dense Crowdâ€, Conference on Computer Vision and Pattern Recognition, (2008).

      [13] Brostow GJ & Cipolla R, “Unsupervised Bayesian Detection of Independent Motion in Crowdsâ€, Conference on Computer Vision and Pattern Recognition, (2006), pp.594–601.

      [14] Nillius P, Sullivan J & Carlsson S, “Multi-Target Tracking - Linking Identities Using Bayesian Network Inferenceâ€, Conference on Computer Vision and Pattern Recognition, (2006), pp.2187– 2194.

      [15] Khan S & Shah M, “Tracking Multiple Occluding People by Localizing on Multiple Scene Planesâ€, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.31, No.3, (2009), pp.505–519.

      [16] Leibe B, Schindler K & Gool LV, “Coupled Detection and Trajectory Estimation for Multi-Object Trackingâ€, International Conference on Computer Vision, (2007).

      [17] Bellman RE, Dynamic Programming, Princeton University Press, (1957).

      [18] Wolf J, Viterbi A & Dixon G, “Finding the Best Set of K Paths Through a TrellisWith Application to Multi-target Trackingâ€, IEEE Transactions on Aerospace and Electronic Systems, Vol.25, No.2, (1989), pp.287–296.

      [19] Milan A, Schindler K & Roth S, “Detection-and trajectory-level exclusion in multiple object trackingâ€, IEEE CVPR, (2013), pp. 3682–3689.

      [20] Wu Y, Lim J & Yang MH, “Online object tracking: A benchmarkâ€, IEEE Conference on Computer vision and pattern recognition (CVPR), (2013), pp.2411-2418.

      [21] Breitenstein MD, Reichlin F, Leibe B, Koller-Meier E & Van Gool L, “Online multi person tracking-by-detection from a single, un calibrated cameraâ€, IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI), Vol.33, No.9, (2011), pp.1820–1833.

      [22] Segal AV & Reid I, “Latent data association: Bayesian model selection for multi-target trackingâ€, IEEE ICCV, (2013), pp.2904–2911.

      [23] Andriyenko A & Schindler K, “Multi-target tracking by continuous energy minimizationâ€, IEEE CVPR, (2011), pp.1265–1272.

      [24] Riahi D & Bilodeau GA, “Multiple feature fusion in the dempster-shafer framework for multi-object trackingâ€, IEEE Computer and Robot Vision (CRV), (2014), pp.313–320.

      [25] Z Yesembayeva (2018). Determination of the pedagogical conditions for forming the readiness of future primary school teachers, Opción, Año 33. 475-499

      [26] G Mussabekova, S Chakanova, A Boranbayeva, A Utebayeva, K Kazybaeva, K Alshynbaev (2018). Structural conceptual model of forming readiness for innovative activity of future teachers in general education school. Opción, Año 33. 217-240

  • Downloads

  • How to Cite

    Ramalakshmi Kanthimathi, V., & Germanus Alex, M. (2018). Novel Adaptive Background Segmentation Algorithm for Multiple Object Tracking. International Journal of Engineering & Technology, 7(3.27), 407-411. https://doi.org/10.14419/ijet.v7i3.27.17984