Multimedia Tools and Applications

, Volume 76, Issue 8, pp 11021–11035 | Cite as

Pedestrian tracking for infrared image sequence based on trajectory manifold of spatio-temporal slice

Article

Abstract

The research of pedestrian tracking in infrared image sequences is a curial part of video surveillance. Considering the particular characteristics of the infrared image, such as low contrast, fuzzy edge and unknown noises interference, the study of infrared pedestrian tracking algorithm becomes a great challenge. Spatio-temporal slice method is effective due to considering both spatial and time scale. It can extract the trajectory of moving targets, reflecting the trajectory manifold variations of targets along the time, to provide ways to depict the regions of targets. However, traditional spatio-temporal based methods only consider the horizontal slice analysis and usually require a large amount of calculation time; this paper proposes a spatio-temporal tracking algorithm to infrared image sequences, using both horizontal and vertical multi-layer slices to obtain the integral trajectory manifold. The integral trajectory is analyzed to obtain the target boundary and position information, with which the target can be tracked in each frame. The experimental results show that the proposed method has a relatively high tracking accuracy with a fast computing speed. Moreover, it can perform effectively in different infrared image sequences with various motion modes by single pedestrian from OTCBVS/05 Terravic Motion IR Database.

Keywords

Spatio-temporal slice Trajectory manifold Pedestrian tracking Infrared image sequence 

Notes

Acknowledgments

This work is supported by National Natural Science Foundation of China, No. 61272358.

References

  1. 1.
    Adelson EH, Bergen JR (1985) Spatiotemporal energy models for the perception of motion[J]. JOSA A 2(2):284–299CrossRefGoogle Scholar
  2. 2.
    Bai Y, Tang M (2012) Robust tracking via weakly supervised ranking svm[C]. IEEE Conf Comput Vis Pattern Recogn:1854–1861Google Scholar
  3. 3.
    Corvee E, Bremond F (2010) Body parts detection for people tracking using trees of histogram of oriented gradient descriptors[C]. IEEE Int Conf Adv Video Signal Based Surveill:469–475Google Scholar
  4. 4.
    Guo JM, Hsia CH, Liu YF et al (2013) Fast background subtraction based on a multilayer codebook model for moving object detection[J]. Circ Syst Video Technol IEEE Tran 23(10):1809–1821CrossRefGoogle Scholar
  5. 5.
    Hsia KH, Lien SF, Su JP (2013) Moving target tracking based on CamShift approach and Kalman filter[J]. Appl Math Inf Sci 7(1):193–200MathSciNetCrossRefGoogle Scholar
  6. 6.
    Khan SM, Shah M (2006) A multiview approach to tracking people in crowded scenes using a planar homography constraint[J]. Lect Notes Comput Sci 3954:133–146CrossRefGoogle Scholar
  7. 7.
    Leichter I, Lindenbaum M, Rivlin E (2010) Mean shift tracking with multiple reference color histograms[J]. Comput Vis Image Underst 114(3):400–408CrossRefGoogle Scholar
  8. 8.
    Lin W, Zhang Y, Lu J, Zhou B, Wang J, Zhou Y (2015) Summarizing surveillance videos with local-patch-learning-based abnormality detection, blob sequence optimization, and synopsis[J]. Neurocomputing 155:84–98CrossRefGoogle Scholar
  9. 9.
    Nanda H, Davis L (2002) Probabilistic template based pedestrian detection in infrared videos[C]. In proceedings of the IEEE Intelligent Vehicle Symposium 1:15–20Google Scholar
  10. 10.
    Ngo CW, Pong TC, Zhang HJ et al (2000) Motion characterization by temporal slices analysis[C]. IEEE Conference on Computer Vision and Pattern Recognition. IEEE Comput Soc:2768–2768Google Scholar
  11. 11.
    Ngo CW, Pong TC, Zhang HJ (2003) Motion analysis and segmentation through spatio-temporal slices processing[J]. IEEE Trans Image Process 12(3):341–355CrossRefGoogle Scholar
  12. 12.
    Ning J, Zhang L, Zhang D et al (2009) Robust object tracking using joint color-texture histogram[J]. Int J Pattern Recognit Artif Intell 23(07):1245–1263CrossRefGoogle Scholar
  13. 13.
    Qian C, Sun X, Wei Y et al (2014) Realtime and Robust Hand Tracking from Depth[C]. IEEE Conference on Computer Vision & Pattern Recognition. IEEE Comput Soc:1106–1113Google Scholar
  14. 14.
    Ricquebourg Y, Bouthemy P (2000) Real-time tracking of moving persons by exploiting spatio-temporal image slices[J]. IEEE Trans Pattern Anal Mach Intell 22(8):797–808CrossRefGoogle Scholar
  15. 15.
    Sato K, Aggarwal JK (2004) Temporal spatio-velocity transform and its application to tracking and interaction[J]. Comput Vis Image Underst 96(2):100–128CrossRefGoogle Scholar
  16. 16.
    Sridhar S, Oulasvirta A, Theobalt C (2013) Interactive markerless articulated hand motion tracking using RGB and depth data[C]. IEEE International Conference on Computer Vision. IEEE Comput Soc:2456–2463Google Scholar
  17. 17.
    Terravic Research Infrared Database. IEEE OTCBVS WS Series BenchGoogle Scholar
  18. 18.
    Toyofuku K, Katsuno T, Hagisato Y (2008) etc. Night view system with pedestrian detection using near infrared light[J]. Toyota Tech Rev 56(1):82–87Google Scholar
  19. 19.
    Wang X, Tang Z (2010) Modified particle filter-based infrared pedestrian tracking[J]. Infrared Phys Technol 53(4):280–287CrossRefGoogle Scholar
  20. 20.
    Xu F, Liu X, Fujimura K (2005) Pedestrian detection and tracking with night vision[J]. IEEE Trans Intell Transp Syst 6(1):63–71CrossRefGoogle Scholar
  21. 21.
    Yang J, Su X, Ma P (2010) Fast pedestrian detection using slice-based motion analysis[C]. Int Conf Pervasive Comput Signal Process Appl:74–77Google Scholar
  22. 22.
    Zhang R, Ge P, Zhou X et al (2013) An method for vehicle-flow detection and tracking in real-time based on Gaussian mixture distribution[J]. Adv Mech Eng 5(4):861321–861321Google Scholar
  23. 23.
    Zhang Y, Lin W, Zhang G et al (2014) A new approach for extracting and summarizing abnormal activities in surveillance videos[C]. IEEE International Conference on Multimedia & Expo Workshops. IEEE:1–5Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijingChina

Personalised recommendations