Accelerations of a 3D Tracking Method for Non-Rigid Objects
| Autor: | Junichi Masaki, Martial Hebert, Eiji Kondo, Norio Okada |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Computer science
business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Point set registration Spline (mathematics) symbols.namesake Mach number Robustness (computer science) 3d tracking symbols Robot Computer vision Artificial intelligence Thin plate spline business Rigid transformation ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Proceedings, 2005 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.. |
| Popis: | This study aims to track a non-rigidly deformable object in real-time using successive range images. Our approach assumes that the object is globally rigid and partially non-rigid during a short interval between 3D snapshots. The tracking process consists of 3 steps; estimating the rigid transformation by ICP algorithm, extracting the non-rigidly deformed areas, and estimating their deformation vectors by Thin Plate Spline Robust Point Matching (TPS-RPM) algorithm. In our past research, it took mach time for estimating the deformation vectors. Then, in this paper, techniques for accelerating the tracking process are described. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|