The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

Silhouette-based Gait Recognition using PBAS

PBAS를 이용한 실루엣 기반 걸음걸이 인식

  • 한영환 (상지대학교 컴퓨터정보공학부)
  • Received : 2014.05.26
  • Accepted : 2014.06.12
  • Published : 2014.07.31
⟨ Previous Next ⟩

Abstract

In this paper, a simple but efficient gait recognition method using spatial-temporal silhouette analysis is proposed. For each image sequence, a background subtraction algorithm and a PBAS(pixel based adaptive segmenter) procedure are first used to segment the moving silhouettes of a walking figure. Gait period estimation is an important step in the gait recognition framework. Therefore, the gait cycle detection algorithm based on the width of the bounding box is applied. Then, to identify people, the step count and stride length of walking figure is obtained in silhouette images. Extensive experiments on the CASIA dataset including 124 subjects have been carried out to demonstrate the effectiveness of the proposed method. As a result, the proposed system are believed to have a sufficient feasibility for the application to gait recognition.

본 논문에서는 시공간 실루엣 분석을 사용하여 간단하지만 효율적인 걸음걸이 인식 방법을 제안한다. 각각의 이미지 시퀀스에 대해, 먼저 차영상 기법과 화소기반 적응분할기법이 보행자의 실루엣을 분할하는데 사용된다. 보행 간격의 추정은 보행 인식 구조에서 중요한 단계이다. 그러므로 경계 사각형의 폭을 기반으로 하는 보행 주기 검출 알고리즘을 사용한다. 그 후, 사람을 인식하기 위하여 보행하는 사람의 걸음수와 보폭이 실루엣 영상에서 구해진다. 124개의 객체를 포함하는 CASIA 데이터 집합에서의 광범위한 실험이 제안된 방법의 유효성을 보여주기 위하여 수행되었다. 그 결과, 제안된 시스템은 보행자 인식에 대한 응용을 위해 충분한 적용 가능성이 있을 것으로 판단된다.

Keywords

Acknowledgement

Supported by : 상지대학교

References

  1. Sruti Das Choudhury and Tardi Tjahjadi, "Silhouette-based gait recognition using Procrustes shape analysis and elliptic Fourier descriptors", Pattern Recognition, Vol. 45, pp. 3414-3426, Sep. 2012. https://doi.org/10.1016/j.patcog.2012.02.032
  2. Zongyi Liu, Laura Malave, and Sudeep Sarkar, "Studies on Silhouette Quality and Gait Recognition", Proc. of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 704-711, June 2004.
  3. Liang Wang, Tieniu Tan, Huazhong Ning, and Weiming Hu, "Silhouette Analysis-Based Gate Recognition for Human Identification", IEEE Trans. on PAMI, Vol. 25, No. 12, pp. 1505-1518, Dec. 2003. https://doi.org/10.1109/TPAMI.2003.1251144
  4. Arihant Kochhar, Divyesh Gupta, Madasu Hanmanlu, and Shantaram Vasikarla, "Silhouette based gait recognition based on the area features using both model free and model based approaches", 2013 IEEE International Conference on Technologies for Homeland Security, pp. 547-551, Nov. 2013.
  5. Minjae Kim and Daeseong Kang, "The Suspicious Pedestrian Detection from Region Area using the SVM Algorithm with the Physical Characteristics", Jounal of KIIT, Vol. 11, No. 12, pp. 71-77, Dec. 2013.
  6. Jihye Jeon, Daehee Kim, YoonKi Yang, Joonki Paik, and Changsu Lee, "Image Distortion Compensation for Improved Gait Recognition", Jour. of The Institute of Electronics Engineers of Korea, Vol. 46.SP, No. 4, pp. 97-106, July 2009.
  7. M. Hofmann, P. Tiefenbacher, and G. Rigoll, "Background Segmentation with Feedback: The Pixel-Based Adaptive Segmenter", IEEE Computer Society Conf. on Computer Vision and Pattern Recognition Workshops, pp. 38-43, June 2012.
  8. Woon Cho, Donghyeon Kim, and Joonki Paik, "Gait Recognition Using Multiple Feature Detection", Jour. of The Institute of Electronics Engineers of Korea, Vol. 44.SP, No. 6, pp. 84-92, Nov. 2007.
  9. Seonguk Jeong and Janghui Yu, "Gait Recognition Technique for Intelligent Surveillance", Korea Information Processing Society Review, Vol. 20, No. 3, pp.50-59, May 2013.
  10. CASIA Gait Database : http://www.sinobiometrics.com/resources.htm.