- 期刊
- OpenAccess
Pose Estimation Using Redundant Measurements and Polar-decomposition Filtering
並列摘要
Rigid-body pose estimation is a recurrent problem that arises in many application areas, such as robotics, rehabilitation and assembly. As such, the problem has been the subject of intensive research, and it still is. The motivation behind the procedure reported here is the calibration of a spherical parallel manipulator, the Agile Wrist, intended to be used as the pitch-roll-yaw joystick of a haptic device. The procedure is based on redundant measurements, to filter measurement noise, and polardecomposition filtering, to extract the orthogonal factor of a still-noisy estimate. The measurement system is a binocular camera. The reported results show an acceptable performance of both the data-acquisition system and the computational procedure.
延伸閱讀
- 盧家賢（2016）。Design and Implementation of a Real-Time RGB-D Visual Pose Estimation Algorithm〔碩士論文，淡江大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0002-0109201615154900
- Huang, H. L. (2022). 6-DoF Object Pose Estimation via Key Component Registration [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU202203645
- Huang, S. S. (2007). Foreground Segmentation and Human Pose Estimation [doctoral dissertation, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2007.00333
- Ma, R., Zhang, J., & Qi, Y. (2020). Overview of 2D Human Pose Estimation. World Scientific Research Journal, 6(1), 196-202. https://doi.org/10.6911/WSRJ.202001_6(1).0028
- Wu, X., & Zhong, B. (2022). Research on 2D Human Pose Estimation Based on Deep Learning. World Scientific Research Journal, 8(6), 47-53. https://doi.org/10.6911/WSRJ.202206_8(6).0007