Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Design and Development of the Multiple Kinect Sensor-based Exercise Pose Estimation System

다중 키넥트 센서 기반의 운동 자세 추정 시스템 설계 및 구현

  • Cho, Yongjoo (Department of Computer Science, Sangmyung University) ;
  • Park, Kyoung Shin (Department of Applied Computer Engineering, Dankook University)
  • Received : 2017.01.09
  • Accepted : 2017.01.25
  • Published : 2017.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this research, we developed an efficient real-time human exercise pose estimation system using multiple Kinects. The main objective of this system is to measure and recognize the user's posture (such as knee curl or lunge) more accurately by employing Kinects on the front and the sides. Especially it is designed as an extensible and modular method which enables to support various additional postures in the future. This system is configured as multiple clients and the Unity3D server. The client processes Kinect skeleton data and send to the server. The server performs the multiple-Kinect calibration process and then applies the pose estimation algorithm based on the Kinect-based posture recognition model using feature extractions and the weighted averaging of feature values for different Kinects. This paper presents the design and implementation of the human exercise pose estimation system using multiple Kinects and also describes how to build and execute an interactive Unity3D exergame.

본 연구에서는 다수의 키넥트 센서를 이용하여 효율적인 실시간 운동 자세 추정 시스템을 설계하고 개발하였다. 이 시스템은 정면과 측면에 키넥트 센서를 사용하여, 한 개로 추적이 어려웠던 사용자의 특정 자세 (예를 들어, 무릎컬 또는 런지)를 보다 정확하게 측정하고 인식하는 것을 목적으로 한다. 그리고 추후 다양한 자세를 지원할 수 있도록 확장 가능하고 모듈화 된 방법으로 설계되었다. 이 시스템은 여러 클라이언트와 유니티 3D 서버로 구성된다. 클라이언트는 키넥트 골격 데이터를 처리하여 서버로 전송한다. 서버는 다중 키넥트를 보정하고, 각도와 거리를 기반으로 한 특징 값 추출하며 여러 대의 키넥트로부터 계산된 특징 값의 가중 평균을 사용하여 자세 인식 모델을 기반으로 자세 추정 알고리즘을 적용한다. 본 논문은 다중 키넥트 센서를 이용한 인간 운동 자세 추정 시스템의 설계 및 구현 방법을 제시하고, 체험형 유니티 3D 운동 게임에 적용한 예시를 설명한다.

Keywords

References

  1. E. Brox, L.F. Luque, G.J. Evertsen, J.E.G. Hernandez, "Exergames for elderly: Social exergames to persuade seniors to increase physical activity," Proceedings of the 5th IEEE International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops, Dublin, May 23-26, pp. 546-549, 2011.
  2. K. S. Park, "Development of Kinect-based Pose Recognition Model for Exercise Game," KIPS Transactions on Computer and Communication Systems, vol. 5, no. 10, pp. 303-310, Oct. 2016. https://doi.org/10.3745/KTCCS.2016.5.10.303
  3. Y. J. Na, H. Jung, C. Wang, and S. D. Min, "Design of Game Contents for Dementia Prevention using Kinect," in Proceedings of Bio-Medical System Conference, Hoengseong-gun Gangwon-do, pp. 13-15, 2015.
  4. G.-F. He, J.-W. Park, S.-K. Kang, and S.-T. Jung, "Development of Gesture Recognition-Based 3D Serious Games," Journal of Korea Game Society, vol. 11, no. 6, pp. 103-114, Nov. 2011.
  5. K. S. Kim, Y. J. Lee, and S. S. Oh, "Development of Analysis of a Walking Game 'Paldokangsan3' Using Kinect," Journal of Korea Game Society, vol. 14, no. 1, pp. 49-58, Jan. 2014. https://doi.org/10.7583/JKGS.2014.14.1.49
  6. J. G. Kim, S.-G. Kim, Y. H. Joo, and J. B. Park, "Human posture recognition using Kinect sensor" in Proceedings of 43rd Annual Conference of the Korean Institute of Electrical Engineers, Jeongseon-gun, Gangwon-do, pp. 1371-1372, 2012.
  7. S. Cho, H. Byun, H. K. Lee, and J. Cha, "Arm Gesture Recognition for Shooting Games based on Kinect Sensor," Journal of KIISE: Software and Applications, vol. 39, no. 10, pp. 796-805, 2012.
  8. H. S. Choi, "Kinect-based Motion Recognition Model for the 3D Contents Control," Journal of the Korea Contents Association, vol. 14, no. 1, pp.24-29, Jan. 2014. https://doi.org/10.5392/JKCA.2014.14.01.024
  9. J. Yang, H. Li, and Y. Jia, "Go-ICP: Solving 3D Registration Efficiently and Globally Optimally," in Proceedings of IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, pp. 1457-1464, 2013.
  10. D. H. Seo, K. S. Park, and D. K. Kim, "Design and Development of Virtual Reality Exergame using Smart Mat and Camera Sensor," Journal of the Korea Institute of Information and Communication Engineering, vol. 20, no. 12, pp.2297-2304, Dec. 2016. https://doi.org/10.6109/jkiice.2016.20.12.2297