Reference : Mid-Air: A multi-modal dataset for extremely low altitude drone flights
Scientific congresses and symposiums : Paper published in a journal
Engineering, computing & technology : Electrical & electronics engineering
http://hdl.handle.net/2268/234665
Mid-Air: A multi-modal dataset for extremely low altitude drone flights
English
Fonder, Michaël mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Van Droogenbroeck, Marc mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Jun-2019
IEEE Conference on Computer Vision and Pattern Recognition Workshops Proceedings
Yes
No
International
IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) - UAVision
from 16-06-2019 to 20-06-2019
IEEE
Long Beach
CA, USA
[en] Mid-Air ; UAV ; Drone ; Multi-modal ; RGB images ; Depth ; Drone flight ; Unstructured environment ; Positioning ; Dataset ; Database ; Benchmark
[en] Flying a drone in unstructured environments with varying conditions is challenging. To help producing better algorithms, we present Mid-Air, a multi-purpose synthetic dataset for low altitude drone flights in unstructured environments. It contains synchronized data of multiple sensors for a total of 54 trajectories and more than 420k video frames simulated in various climate conditions. In this work, we motivate design choices, explain how the data was simulated, and present the content of the dataset. Finally, a benchmark for positioning and a benchmark for image generation tasks show how Mid-Air can be used to set up a standard evaluation method for assessing computer vision algorithms in terms of robustness and generalization. We illustrate this by providing a baseline for depth estimation and by comparing it with results obtained on an existing dataset. The Mid-Air is publicly downloadable, with additional details on the data format and organization, at http://midair.ulg.ac.be
Montefiore Institute of Electrical Engineering and Computer Science - Montefiore Institute ; Telim
Researchers ; Professionals ; Students
http://hdl.handle.net/2268/234665
http://midair.ulg.ac.be

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Fonder2019MidAir.pdfMid-Air: A multi-modal dataset for extremely low altitude drone flightsAuthor postprint4.68 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.