Abstract
Motion and dynamic environments, especially under challenging lighting conditions, are still an open issue in the field of computer vision. In this paper, we propose an online, end-to-end pipeline for real-time, low latency, 6 degrees-of-freedom pose estimation and tracking of fiducial markers. We employ the high-speed abilities of event-based sensors to directly refine spatial transformations. Furthermore, we introduce a novel two-way verification process for detecting tracking errors by backtracking the estimated pose, allowing to evaluate the quality of our tracking. This approach allows us to achieve pose estimation with an average latency lower than 3 ms and with an average error lower than 5 mm.
Originalsprache | Englisch |
---|---|
Titel | Proceedings of the Fifteenth International Conference on Machine Vision (ICMV 2022) |
Redakteure/-innen | Wolfgang Osten, Dmitry P. Nikolaev, Jianhong (Jessica) Zhou |
Band | 12701 |
DOIs | |
Publikationsstatus | Veröffentlicht - 7 Juni 2023 |
Veranstaltung | Fifteenth International Conference on Machine Vision (ICMV 2022) - Rome, Rome, Italien Dauer: 18 Nov. 2022 → 20 Nov. 2022 |
Konferenz
Konferenz | Fifteenth International Conference on Machine Vision (ICMV 2022) |
---|---|
Kurztitel | ICMV 2022 |
Land/Gebiet | Italien |
Stadt | Rome |
Zeitraum | 18/11/22 → 20/11/22 |
Research Field
- High-Performance Vision Systems