DOI | Resolve DOI: https://doi.org/10.1109/CRV55824.2022.00035 |
---|
Author | Search for: Abdollahzadeh, Sakineh; Search for: Proulx, Pier-Luc; Search for: Allili, Mohand Said; Search for: Lapointe, Jean-Francois1 |
---|
Affiliation | - National Research Council of Canada. Digital Technologies
|
---|
Funder | Search for: National Research Council of Canada's Artificial Intelligence |
---|
Format | Text, Article |
---|
Conference | 2022 19th Conference on Robots and Vision (CRV), May 31 - June 2, 2022, Toronto, ON, Canada |
---|
Subject | automatic UAV navigation; safe landing zones (SLZ); semantic segmentation; deep regression; image segmentation; three-dimensional displays; navigation; urban areas; semantics; vision sensors; predictive models |
---|
Abstract | Finding safe landing zones (SLZ) in urban areas and natural scenes is one of the many challenges that must be overcome in automating Unmanned Aerial Vehicles (UAV) navigation. Using passive vision sensors to achieve this objective is a very promising avenue due to their low cost and the potential they provide for performing simultaneous terrain analysis and 3D reconstruction. In this paper, we propose using a deep learning approach on UAV imagery to assess the SLZ. The model is built on a semantic segmentation architecture whereby thematic classes of the terrain are mapped into safety scores for UAV landing. Contrary to past methods, which use hard classification into safe/unsafe landing zones, our approach provides a continuous safety map that is more practical for an emergency landing. Experiments on public datasets have shown promising results. |
---|
Publication date | 2022-05-31 |
---|
Publisher | IEEE |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | b594c65b-af7a-4004-bd4a-2a2ac9748554 |
---|
Record created | 2022-09-09 |
---|
Record modified | 2023-03-16 |
---|