상세정보
학술대회
Real-time Upper-body Human Pose Estimation from Depth Data using Kalman Filter for Simulator
- 발행일
- 201405
- 출처
- International Conference on Applications of Optics and Photonics 2014, pp.1-9
- 협약과제
- 13VC5300, 잠재 역량 진단을 위한 감정특이점 기반 맞춤형 인지센싱 및 플랫폼 기술개발, 윤호섭
- 초록
- Recently, many studies show that an indoor horse riding exercise has a positive effect on promoting health and diet. However, if a rider has an incorrect posture, it will be the cause of back pain. In spite of this problem, there is only few research on analyzing rider's posture. Therefore, the purpose of this study is to estimate a rider pose from a depth image using the Asus's Xtion sensor in real time. In the experiments, we show the performance of our pose estimation algorithm in order to comparing the results between our joint estimation algorithm and ground truth data.
- KSP 제안 키워드
- Back pain, Depth Data, Depth image, Ground truth data, Horse Riding, Human pose estimation, Joint Estimation, Real-Time, estimation algorithm, kalman filter