Multimedia Tools and Applications

, Volume 50, Issue 1, pp 75–94 | Cite as

Performance analysis for automated gait extraction and recognition in multi-camera surveillance

  • Michela Goffredo
  • Imed BouchrikaEmail author
  • John N. Carter
  • Mark S. Nixon


Many studies have confirmed that gait analysis can be used as a new biometrics. In this research, gait analysis is deployed for people identification in multi-camera surveillance scenarios. We present a new method for viewpoint independent markerless gait analysis that does not require camera calibration and works with a wide range of walking directions. These properties make the proposed method particularly suitable for gait identification in real surveillance scenarios where people and their behaviour need to be tracked across a set of cameras. Tests on 300 synthetic and real video sequences, with subjects walking freely along different walking directions, have been performed. Since the choice of the cameras’ characteristics is a key-point for the development of a smart surveillance system, the performance of the proposed approach is measured with respect to different video properties: spatial resolution, frame-rate, data compression and image quality. The obtained results show that markerless gait analysis can be achieved without any knowledge of camera’s position and subject’s pose. The extracted gait parameters allow recognition of people walking from different views with a mean recognition rate of 92.2% and confirm that gait can be effectively used for subjects’ identification in a multi-camera surveillance scenario.


Gait analysis Gait recognition Biometrics Multi-view Surveillance Object handover 



This research is supported by the SCOVIS project (ICT FP7-216465) funded by European Union under the seventh research program.


  1. 1.
    BenAbdelkader C, Davis LS, Cutler R (2002) Motion-based recognition of people in eigengait space. In: Proc IEEE conf AFG, pp 267–274.
  2. 2.
    Bhanu B, Han J (2003) Human recognition on combining kinematic and stationary features. In: Proc int conf AVBPA, pp 600–608Google Scholar
  3. 3.
    Black J, Ellis T, Rosin P (2002) Multi view image surveillance and tracking. In: Workshop on motion and video computing. Proc, pp 169–174. doi: 10.1109/MOTION.2002.1182230
  4. 4.
    Bouchrika I, Nixon MS (2007) Gait-based pedestrian detection for automated surveillance. In: International conference on computer vision systemsGoogle Scholar
  5. 5.
    Bouchrika I, Nixon MS (2007) Model-based feature extraction for gait analysis and recognition. In: LNCS, vol 4418. Springer, New YorkGoogle Scholar
  6. 6.
    Cai Y, Chen W, Huang K, Tan T (2007) Continuously tracking objects across multiple widely separated cameras. In: ACCV (1), pp 843–852Google Scholar
  7. 7.
    Casia gait database (2006).
  8. 8.
    Chau T (2001) A review of analytical techniques for gait data. Part 1: fuzzy, statistical and fractal methods. Gait Posture 13(1):49–66CrossRefMathSciNetGoogle Scholar
  9. 9.
    Chilgunde A, Kumar P, Ranganath S, WeiMin H (2004) Multi-camera target tracking in blind regions of cameras with non-overlapping fields of view. In: British machine vision conferenceGoogle Scholar
  10. 10.
    Collins R, Gross R, Shi J (2002) Silhouette-based human identification from body shape and gait. In: Proc. IEEE conf. on automatic face and gesture recognition, pp 351–356Google Scholar
  11. 11.
    Cutting J, Kozlowski L (1977) Recognizing friends by their walk: gait perception without familiarity cues. Bull Psychon Soc 9:353–356Google Scholar
  12. 12.
    Dempster WT, Gaughran GRL (1965) Properties of body segments based on size and weight. Am J Anat 120:33–54CrossRefGoogle Scholar
  13. 13.
    Fisher R (2002) Self-organization of randomly placed sensors, p IV: 146 ffGoogle Scholar
  14. 14.
    Gilbert A, Bowden R (2006) Tracking objects across cameras by incrementally learning inter-camera colour calibration and patterns of activity, pp 125–136Google Scholar
  15. 15.
    Goffredo M, Seely RD, Carter JN, Nixon MS (2008) Markerless view independent gait analysis with self-camera calibration. In: Proc. IEEE conf. on automatic face and gesture recognitionGoogle Scholar
  16. 16.
    Goffredo M, Spencer N, Pearce D, Carter JN, Nixon MS (2007) Human perambulation as a self calibrating biometric. In: LNCS, vol 4778. Springer, New YorkGoogle Scholar
  17. 17.
    Gross R, Shi J (2001) The cmu motion of body (mobo) database. Tech. Rep. CMU-RI-TR-01-18, Robotics Institute, Carnegie Mellon University, PittsburghGoogle Scholar
  18. 18.
    Haralick RM, Shapiro LG (1992) Computer and robot vision, vol 1. Addison-Wesley, ReadingGoogle Scholar
  19. 19.
    Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. IEEE Trans Syst Man Cybern 34(3):334–352. doi: 10.1109/TSMCC.2004.829274 CrossRefGoogle Scholar
  20. 20.
    Huang P, Harris C, Nixon M (1999) Recognising humans by gait via parametric canonical space. J Artif Intell Eng 13(4):359–366CrossRefGoogle Scholar
  21. 21.
    Huang T, Russell S (1997) Object identification in a Bayesian context. In: IJCAI97, pp 1276–1282Google Scholar
  22. 22.
    Ilie A, Welch G (2005) Ensuring color consistency across multiple cameras. In: Tenth IEEE conf. on computer vision, vol 2, pp 1268–1275. doi: 10.1109/ICCV.2005.88
  23. 23.
    Javed O, Rasheed Z, Shafique K, Shah M (2003) Tracking across multiple cameras with disjoint views. In: Proc. ninth IEEE conf. on computer vision, vol 2, pp 952–957. doi: 10.1109/ICCV.2003.1238451
  24. 24.
    Kale A, Chowdhury A, Chellappa R (2003) Towards a view invariant gait recognition algorithm. In: Proc IEEE conf AVSS, pp 143–150Google Scholar
  25. 25.
    Kang S, Min J, Paik JK (2001) Multiple-camera tracking system with seamless object handover. SPIE, pp 27–34. doi: 10.1117/12.424949.
  26. 26.
    Khan S, Shah M (2003) Consistent labeling of tracked objects in multiple cameras with overlapping fields of view. IEEE Trans Pattern Anal Mach Intell 25(10):1355–1360. doi: 10.1109/TPAMI.2003.1233912 CrossRefGoogle Scholar
  27. 27.
    Kettnaker V, Zabih R (1999) Bayesian multi-camera surveillance. IEEE Conf Comput Vision Pattern Recogn 2:259. doi: 10.1109/CVPR.1999.784638 Google Scholar
  28. 28.
    Makris D, Ellis T, Black J (2004) Bridging the gaps between cameras. In: Proc IEEE Comput Vis Pattern Recognit 2:II–205–II–210. doi: 10.1109/CVPR.2004.1315165
  29. 29.
    Middleton L, Wagg DK, Bazin AI, Carter JN, Nixon MS (2006) Developing a non-intrusive biometric environment. In: Proc IEEE int conf IROS, pp 723–728. doi: 10.1109/IROS.2006.282619
  30. 30.
    Murray MP, Drought AB, Kory RC (1964) Walking patterns of normal men. J Bone Joint Surg 46:335Google Scholar
  31. 31.
    Niu C, Grimson E (2006) Recovering non-overlapping network topology using far-field vehicle tracking data. In: ICPR (4), pp 944–949Google Scholar
  32. 32.
    Nixon M, Aguado A (2007) Feature extraction & image processing, 2nd edn. Academic, LondonGoogle Scholar
  33. 33.
    Nixon MS, Carter JN (2006) Automatic recognition by gait. Proc IEEE 94(11):2013–2024CrossRefGoogle Scholar
  34. 34.
    Orrite-Urunuela C, del Rincon J, Herrero-Jaraba J, Rogez G (2004) 2d silhouette and 3d skeletal models for human detection and tracking. Proc IEEE Conf ICPR 4:244–247Google Scholar
  35. 35.
    Phillips PJ, Moon H, Rizvi SA, Rauss PJ (2000) The FERET evaluation methodology for face recognition algorithms. IEEE Trans Pattern Anal Mach Intell 22(10):1090–1104CrossRefGoogle Scholar
  36. 36.
    Phillips P, Sarkar S, Robledo I, Grother P, Bowyer K (2002) The gait identification challenge problem: data sets and baseline algorithm. Proc Int Conf Pattern Recogn 1:385–388. doi: 10.1109/ICPR.2002.1044731 Google Scholar
  37. 37.
    Rahimi A, Dunagan B, Darrell T (2004) Simultaneous calibration and tracking with a network of non-overlapping sensors. Proc Comput Vision Pattern Recogn 1:I–187–I–194. doi: 10.1109/CVPR.2004.1315031 Google Scholar
  38. 38.
    Sardis M, Anagnostopoulos V, Doulamis N (2009) Applied surveillance using biometrics on agents infrastructures. In: 5th Conference on artificial intelligence applications and innovations, Greek, April 2009Google Scholar
  39. 39.
    Shutler J, Grant M, Nixon MS, Carter JN (2002) On a large sequence-based human gait database. In: Proc int conf recent advances in soft computing, pp 66–72Google Scholar
  40. 40.
    Stillman S, Essa I (2001) Towards reliable multimodal sensing in aware environments. In: PUI ’01: proc. workshop on perceptive user interfaces. ACM, New York, pp 1–6 doi:10.1145/971478.971499 CrossRefGoogle Scholar
  41. 41.
    Tieu K, Dalley G, Grimson W (2005) Inference of non-overlapping camera network topology by measuring statistical dependence. In: Tenth IEEE conf. on computer vision, vol 2, pp 1842–1849. doi: 10.1109/ICCV.2005.122
  42. 42.
    Veres G, Gordon L, Carter JN, Nixon MS (2004) What image information is important in silhouette-based gait recognition? Proc IEEE Conf CVPR 2:II–776–II–782Google Scholar
  43. 43.
    Wang L, Tan T, Hu W, Ning H (2003) Automatic gait recognition based on statistical shape analysis. IEEE Trans IP 12(9):1120–1131MathSciNetGoogle Scholar
  44. 44.
    Wang L, Tan T, Ning H, Hu W (2003) Silhouette analysis-based gait recognition for human identification. IEEE Trans PAMI 25(12):1505–1518Google Scholar
  45. 45.
    Yamada Y (1999) Advanced method for improvement of obscure video image. In: Proc. IEEE 33rd annual carnahan conference on security technology, pp 440–445Google Scholar
  46. 46.
    Zhang R, Vogler C, Metaxas D (2007) Human gait recognition at sagittal plane. J Image Vis Comput 25(3):321–330CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Michela Goffredo
    • 1
  • Imed Bouchrika
    • 1
    Email author
  • John N. Carter
    • 1
  • Mark S. Nixon
    • 1
  1. 1.School of Electronics and Computer ScienceUniversity of SouthamptonSouthamptonUK

Personalised recommendations