Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Human gait identification from extremely low-quality videos: an enhanced classifier ensemble method

© The Institution of Engineering and Technology
Received 20/08/2013, Accepted 28/01/2014, Revised 14/12/2013, Published 15/04/2014

Nowadays, surveillance cameras are widely installed in public places for security and law enforcement, but the video quality may be low because of the limited transmission bandwidth and storage capacity. In this study, the authors proposed a gait recognition method for extremely low-quality videos, which have a frame-rate at one frame per second (1 fps) and resolution of 32 × 22 pixels. Different from popular temporal reconstruction-based methods, the proposed method uses the average gait image (AGI) over the whole sequence as the appearance-based feature description. Based on the AGI description, the authors employed a large number of weak classifiers to reduce the generalisation errors. The performance can be further improved by incorporating the model-based information into the classifier ensemble. The authors found that the performance improvement is directly proportional to the average disagreement level of weak classifiers (i.e. diversity), which can be increased by using the model-based information. The authors evaluated the proposed method on both indoor and outdoor databases (i.e. the low-quality versions of OU-ISIR-D and USF databases), and the results suggest that our method is more general and effective than other state-of-the-art algorithms.

Inspec keywords: visual databases; image classification; object recognition; video signal processing; feature extraction; gait analysis

Other keywords: human gait identification; USF database; storage capacity; low-quality videos; classifier ensemble method; average gait image; outdoor databases; surveillance cameras; gait recognition method; AGI; OU-ISIR-D database; weak classifiers; temporal reconstruction-based methods; model-based information; transmission bandwidth; appearance-based feature description; generalisation error reduction; indoor databases

Subjects: Image recognition; Video signal processing; Computer vision and image processing techniques

References

    1. 1)
      • 14. Makihara, Y., Mannami, H., Tsuji, A., et al: ‘The ou-isir gait database comprising the treadmill dataset’, IPSJ Trans. Comput. Vis. Appl., 2012, 4, pp. 53–62.
    2. 2)
    3. 3)
      • 18. Wang, X., Tang, X.: ‘Random sampling lda for face recognition’. Proc. Conf. Computer Vision and Pattern Recognition, 2004, pp. 259–265.
    4. 4)
    5. 5)
      • 12. Guan, Y., Wei, X., Li, C.-T., et al: ‘Combining gait and face for tackling the elapsed time challenges’. Proc. Int'l Conf. Biometrics: Theory, Applications and Systems, 2013, pp. 1–8.
    6. 6)
      • 2. Al-Huseiny, M., Mahmoodi, S., Nixon, M.: ‘Gait learning-based regenerative model: a level set approach’. Proc. Int'l Conf. Pattern Recognition, 2010, pp. 2644–2647.
    7. 7)
      • 9. Guan, Y., Li, C.-T.: ‘A robust speed-invariant gait recognition system for walker and runner identification’. Proc. Int'l Conf. Biometrics, 2013, pp. 1–8.
    8. 8)
      • 7. Bobick, A., Johnson, A.: ‘Gait recognition using static, activity-specific parameters’. Proc. of Computer Vision and Pattern Recognition, 2001, pp. 423–430.
    9. 9)
    10. 10)
    11. 11)
      • 20. Lovell, B., Bigdeli, A., Mau, S.: ‘Invited paper: embedded face and biometric technologies for national and border security’. Proc. Computer Vision and Pattern Recognition Workshops, 2011, pp. 117–122.
    12. 12)
      • 1. Mori, A., Makihara, Y., Yagi, Y.: ‘Gait recognition using period-based phase synchronization for low frame-rate videos’. Proc. Int'l Conf. Pattern Recognition, 2010, pp. 2194–2197.
    13. 13)
      • 16. Veres, G., Gordon, L., Carter, J., et al: ‘What image information is important in silhouette-based gait recognition?’. Proc. Conf. Computer Vision and Pattern Recognition, 2004, pp. 776–782.
    14. 14)
    15. 15)
      • 10. Guan, Y., Li, C.-T., Hu, Y.: ‘Random subspace method for gait recognition’. Proc. Int'l Conf. Multimedia and Expo Workshops, 2012, pp. 284–289.
    16. 16)
    17. 17)
    18. 18)
      • 4. Akae, N., Makihara, Y., Yagi, Y.: ‘Gait recognition using periodic temporal super resolution for low frame-rate videos’. Proc. Int'l Joint Conf. Biometrics, 2011, pp. 1–7.
    19. 19)
      • 11. Guan, Y., Li, C.-T., Hu, Y.: ‘Robust clothing-invariant gait recognition’. Proc. Int'l Conf. Intelligent Information Hiding and Multimedia Signal Processing, 2012, pp. 321–324.
    20. 20)
      • 6. Guan, Y., Li, C.-T., Choudhury, S.: ‘Robust gait recognition from extremely low frame-rate videos’. Proc. Int'l Workshop on Biometrics and Forensics, 2013, pp. 1–4.
    21. 21)
      • 3. Makihara, Y., Mori, A., Yagi, Y.: ‘Temporal super resolution from a single quasi-periodic image sequence based on phase registration’. Proc. Asian Conf. Computer Vision, 2011, pp. 107–120.
    22. 22)
      • 8. Cunado, D., Nixon, M., Carter, J.: ‘Using gait as a biometric, via phase-weighted magnitude spectra’. Proc. Int'l Conf. Audio- and Video Based Biometric Person Authentication, 1997, pp. 95–102.
    23. 23)
      • 5. Akae, N., Mansur, A., Makihara, Y., et al: ‘Video from nearly still: an application to low frame-rate gait recognition’. Proc. Conf. on Computer Vision and Pattern Recognition, 2012, pp. 1537–1543.
    24. 24)
      • 22. Skalak, D.B.: ‘The sources of increased accuracy for two proposed boosting algorithms’. Proc. American Association for Artificial Intelligence Workshop, 1996, pp. 120–125.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2013.0062
Loading

Related content

content/journals/10.1049/iet-bmt.2013.0062
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address