Target Motion Estimation by Multi-Eye Vision Hand-Arm
In this paper, we propose a “Multi-Eye Vision Hand-Arm,” in which many small high-speed cameras are mounted on the entire body of a hand-arm robot to eliminate blind spots in visual recognition. Also, we propose a method to estimate the trajectory of a moving object by integrating asynchronous visual information from each high-speed camera with a nonlinear Kalman filter. We realized ball tracking and catching to confirm the system’s effectiveness.
Authors
- K. Hibino
- Akio Namiki (ORCID: https://orcid.org/0000-0003-3181-0818)
- Koki Terakado
- Cheng Ju (ORCID: https://orcid.org/0000-0002-2282-6917)
Institutions
- Chiba University (JP)
Publication Details
- Published
- 2024-11-20
- DOI
- https://doi.org/10.1109/cbs61689.2024.10860515
- Primary Topic
- Hand Gesture Recognition Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00