Enhanced real-time 6d pose estimation for automatic recovery of in-flight UAVs using distance-aware keypoint heatmaps
Mingyu Jeong, Andrew Jaeyong Choi · 2025
Read Enhanced real-time 6d pose estimation for automatic recovery of in-flight UAVs using distance-aware keypoint heatmaps by Mingyu Jeong, Andrew Jaeyong Choi (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12804179.txt.
Description
Mingyu Jeong and Andrew Choi improve a vision method that tracks a flying drone so a ground vehicle can recover it, in a 2025 paper. Drones that lose control or lack a runway need safe capture, which demands exact position and tilt in real time. Their system reads a single camera view.
Key points on the drone are found from heat maps whose blur width adapts to the drone's distance. That change lifted correct key point rates by up to two and a half points across several backbones. A geometry solver turns the points into full pose. Tests covered varied heights, steep tilts, and motion blur. Sharper points mean safer catches.
Catalog record
| CREATOR | Mingyu Jeong, Andrew Jaeyong Choi |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |