Detection; Synthetic Data; YOLOv5; Computer vision; Deep Learning
Abstract :
[en] In this paper, we deal with the problem of shadow detection of UAVs, which impacts their navigation. We propose to generate synthetic images containing shadows in random locations, backgrounds, sizes, and opacities in order to augment our dataset. The generated data is used to train and compare several models to effectively detect, in real-time, UAVs shadows which will help to stabilize their localization and navigation. Deep learning models such as SSD, YOLOv3, and YOLOv5 are tested for the detection part. With our approach, we achieved 99\% of the mean average precision when using the YOLOv5.
Disciplines :
Computer science
Author, co-author :
Mokhtari, Mohammed El Amine ; Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Vandenbulcke, Virginie ; Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Laraba, Sohaib ; Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Mancas, Matei ; Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Ennadifi, Elias ; Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Tazir, Mohamed ; Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Gosselin, Bernard ; Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Language :
English
Title :
Semi-synthetic Data for Automatic Drone Shadow Detection
Publication date :
07 October 2022
Journal title :
ESANN
Peer reviewed :
Peer reviewed
Research unit :
F105 - Information, Signal et Intelligence artificielle
Research institute :
R450 - Institut NUMEDIART pour les Technologies des Arts Numériques