한국정보과학회논문지:소프트웨어및응용 (Journal of KIISE:Software and Applications)

한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지

HMM을 이용한 보행자 인식

HMM-Based Human Gait Recognition

  • 신봉기 (부경대학교 컴퓨터공학과) ;
  • 석흥일 (부경대학교 컴퓨터공학과)
  • 발행 : 2006.05.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근, 사람을 인식하는데 있어 걸음걸이가 기존에 사용되어 오던 많은 생체인식을 보완할 만한 것으로 등장하였다. 본 연구는 보행자 실루엣의 동적 특징과 은닉 마르코프 모델(HMM)을 이용한 보행자 인식 방법을 제안한다. 보행자의 보행 모델은 무한 순환 구조의 HMM 두 가지를 사용하였다. 하나는 자기 조직화 지도(SOM)를 벡터 양자화기로 하는 이산 HMM방식이고, 다른 하나는 주성분 분석(PCA) 공간으로 변환된 특징 벡터를 이용하는 연속 HMM방식이다. 실험 결과 HMM이 몇 가지 변수의 조정에 대해 일관성 있는 성능 변화를 보이며 최고 88.1%의 인식률을 기록하였다. 또한 기존 연구 결과와 비교하여 볼 때 특징과 제안 구조의 모델은 보행자 인식에 충분한 적용 가능성이 있으며, 나아가 걸음걸이가 생체 인식으로 이용되기에 좋은 지표가 될 수 있을 것으로 판단된다.

Recently human gait has been considered as a useful biometric supporting high performance human identification systems. This paper proposes a view-based pedestrian identification method using the dynamic silhouettes of a human body modeled with the Hidden Markov Model(HMM). Two types of gait models have been developed both with an endless cycle architecture: one is a discrete HMM method using a self-organizing map-based VQ codebook and the other is a continuous HMM method using feature vectors transformed into a PCA space. Experimental results showed a consistent performance trend over a range of model parameters and the recognition rate up to 88.1%. Compared with other methods, the proposed models and techniques are believed to have a sufficient potential for a successful application to gait recognition.

키워드

참고문헌

  1. G. Johansson 'Visual perception of biological motion and a model for its analysis,' Perception and Psychophysics, vol. 14, no. 2, pp. 201-211, 1973 https://doi.org/10.3758/BF03212378
  2. J. Aggarwal and Q. Cai. 'Human motion analysis -a review,' Computer Vision and Image Under-standing, vol. 73, no. 3, pp. 428-440, March 1999 https://doi.org/10.1006/cviu.1998.0744
  3. D.M. Gavrila. 'The visual analysis of human movement-a survey,' Computer Vision and Image Understanding, vol. 73, pp. 82-98, 1999 https://doi.org/10.1006/cviu.1998.0716
  4. L.R. Rabiner, 'A tutorial on hidden Markov models and selected applications in speech recognition,' Proceedings of the IEEE, vol. 77, no.2, pp.257-285, February 1989 https://doi.org/10.1109/5.18626
  5. A. Kale, A. N. Rajagopalan, A. Sundaresan, N. Cuntoor, A. RoyChowdhury, V. Krueger, R. Chellappa, 'Identification of humans using gait,' IEEE Transactions on Image Processing, September, 2004 https://doi.org/10.1109/TIP.2004.832865
  6. C. Cedras and M. Shah, 'Motion-based recognition -a survey,' Image and Vision Computing, vol. 13, no. 2, pp. 129-155, 1995 https://doi.org/10.1016/0262-8856(95)93154-K
  7. J. Yamato, J. Ohya, and L. Ishii. 'Recognizing human action in time-sequential images using hidden Markov model,' Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 624-630, 1995
  8. A. Kale, A. Rajagopalan, N. Cuntoor, and V. Kruger. 'Gait-based recognition of humans using continuous HMMs,' Proceedings of the IEEE Conference on Automatic Face and Gesture Recognition, pp. 321-326, 2002 https://doi.org/10.1109/AFGR.2002.1004176
  9. J.J. Little and J.E. Boyd. 'Recognizing people by their gait: the shape of motion,' Videre, vol. 1, no. 2, pp. 1-32, 1998
  10. R. Collins, R. Gross, and J. Shi. 'Silhouette-based human identification from body shape and gait,' IEEE Conf Automatic Face and Gesture Recognition, pp. 351-356, 2002 https://doi.org/10.1109/AFGR.2002.1004181
  11. C. BenAbdelkader, R.Cutler, and L.Davis. 'Motion-based recognition of people in eigengait space.' IEEE Conf Automatic Face and Gesture Recognition, pp. 254-259, 2002 https://doi.org/10.1109/AFGR.2002.1004165
  12. S. Jabri, Z. Durie, H. Wechsler, and A. Rosenfeld, 'Detection and location of people in video images using adaptive fusion of color and edge information,' Proceedings of International Conference on Pattern Recognition, pp. 627-630, 2000
  13. http://pages.cpsc.ucalgary.ca/~boyd/gait/experiment.html
  14. Andrew R. Webb, Statistical Pattern Recognition Second Edition, John Wiley and Sons, 2002