Pattern Recognition and Image Analysis

, Volume 25, Issue 3, pp 532–540 | Cite as

An improvement on an MCMC-based video tracking algorithm

  • E. V. Shalnov
  • V. S. Konushin
  • A. S. Konushin
Applied Problems


This paper presents an approach to fully automatic people tracking in surveillance video recorded by stable camera. We propose an improvement on Benfold et al. tracking-by-detection algorithm [1]. We extend the basic algorithm through filtering of person detector results and the scene entrance/exit positions construction. Moreover, the paper presents a modified method for tracklet position estimation. We compare several tracklet construction algorithms such as “Flock of Features” and normalized cross correlation. Our experiments reveal that all the proposed modifications improve both robustness and precision of tracks compared to the basic algorithm.


computer vision biometry video analytics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    B. Benfold and I. Reid, “Stable multi-target tracking in real-time surveillance video,” in Proc. Computer Vision and Pattern Recognition (Colorado Springs, 2011), pp. 3457–3464.Google Scholar
  2. 2.
    M. Breitenstein, F. Reichlin, B. Leibe, E. KollerMeier, and L. Van Gool, “Robust tracking-by-detection using a detector confidence particle filter,” Int. Conf. Comput. Vision, No. 12, 1515–1522 (2009).Google Scholar
  3. 3.
    H. Nguyen and B. Bhanu, “Real-time pedestrian tracking with bacterial foraging optimization,” Adv. Video Signal-Based Surv., No. 9, 37–42 (2012).Google Scholar
  4. 4.
    W. Choi and S. Savarese, “A unified framework for multi-target tracking and collective activity recognition,” Proc. Europ. Conf. Comput. Vision, No. 12, 215–230 (2012).Google Scholar
  5. 5.
    S. Oh, S. Russell, and S. Sastry, “Markov chain Monte Carlo data association for general multiple-target tracking problems,” Decision Control 1 (43), 735–742 (2004).Google Scholar
  6. 6.
    V. Prisacariu and I. Reid, FastHOG–a real-time GPU implementation of HOG. id_tr2310_09/prisacariu_reid_tr2310_09.pdfGoogle Scholar
  7. 7.
    J. Shi and C. Tomasi, “Good features to track,” in Proc. Computer Vision and Pattern Recognition Conf. (Seattle, 1994), pp. 593–600.Google Scholar
  8. 8.
    C. Tomasi and T. Kanade, Detection and Tracking of Point Features. Scholar
  9. 9.
    M. Kolsch and M. Turk, “Fast 2D hand tracking with flocks of features and multi-cue integration,” in Proc. Computer Vision and Pattern Recognition Workshop (Washington, 2004), p. 158.Google Scholar
  10. 10.
    W. Freeman, D. Anderson, P. Beardsley, C. Dodge, M. Roth, C. Weissman, W. Yerazunus, H. Kage, K. Kyuma, Y. Miyake, and K. Tanaka, “Computer vision for interactive computer graphics,” IEEE Comput. Graph. Appl. 18 (3), 42–53 (1998).CrossRefGoogle Scholar
  11. 11.
    B. Fulkerson, A. Vedaldi, and S. Soatto, “Class segmentation and object localization with superpixel neighborhoods,” in Proc. 12th Int. IEEE Conf. on Computer Vision (Kyoto, 2009), pp. 670–677.Google Scholar
  12. 12.
    R. E. Kalman, et al., “A new approach to linear filtering and prediction problems,” J. Basic Eng. 82 (1), 35–45 (1960).CrossRefGoogle Scholar
  13. 13.
    K. Bernardin and R. Stiefelhagen, “Evaluation multiple object tracking performance: the CLEAR MOT metrics,” EURASIP J. Image Video Image Video 1. Processing 2008 (3), 1–10 (2008).CrossRefGoogle Scholar

Copyright information

© Pleiades Publishing, Ltd. 2015

Authors and Affiliations

  • E. V. Shalnov
    • 1
  • V. S. Konushin
    • 2
  • A. S. Konushin
    • 1
  1. 1.Graphics and Media LabMoscow State UniversityMoscowRussia
  2. 2.LLC Video Analysis TechnologiesMoscowRussia

Personalised recommendations