Wu, Zebiao and Marais, Patrick (2026) Layer-Based Multi-Stage UAV Coverage Path Planning for Energy-Efficient Image-Based 3D Site Modeling, Unmanned Systems, World Scientific Publishing Company.
Full text not available from this repository. (Use alternate locations listed below)Abstract
In multirotor-based photogrammetry, high-quality multi-view stereo modeling of a site requires a flight path that captures images from a wide range of viewing angles and altitudes. However, aerodynamic models show that vertical maneuvering consumes notably more energy than horizontal cruising, and flight paths with many vertical transitions therefore lead to rapid battery depletion and lower operational time. Existing planning strategies typically address trajectory generation within continuous spaces, volumetric grids, or fixed uniform layers, but these approaches often fail to limit the vertical search space effectively and struggle to reduce energy usage without sacrificing the specific camera placements needed to reconstruct complex structural details. In this work, we propose a multi-stage planning framework that addresses the trade-off between energy efficiency and reconstruction quality by restricting the sampling space of feasible cameras to a sparse subset of vertical layers. To satisfy photogrammetric requirements within this reduced space, we introduce a view selection scheme based on global co-visibility analysis. This scheme prioritizes surface regions that lack viewpoint observation redundancy and allocates camera viewpoints to capture intricate structural details that might otherwise be inadequately observed. Finally, a path planning stage generates collision-free trajectories within this sparse configuration, and this design implicitly minimizes energy-intensive vertical transitions. Validation on real-world scanned scenes demonstrates that this approach reduces total flight energy by 6%–25% compared to the next most energy-efficient baseline and maintains reconstruction completeness comparable to coverage-driven methods.
| Item Type: | Journal article (paginated) |
|---|---|
| Additional Information: | https://doi.org/10.1142/S230138502850015X |
| Subjects: | Computing methodologies > Artificial intelligence > Computer vision Applied computing |
| Alternate Locations: | https://www.worldscientific.com/doi/10.1142/S230138502850015X |
| Date Deposited: | 08 Sep 2026 07:51 |
| Last Modified: | 08 Sep 2026 07:51 |
| URI: | https://pubs.cs.uct.ac.za/id/eprint/1801 |
Actions (login required)
 |
View Item |