Cafarelli D., Ciampi L., Vadicamo L., Gennaro C., Berton A., Paterni M., Benvenuti C., Passera M., Falchi F.
Object detection Man overboard Deep learning Unmanned Aerial Vehicles
Modern Unmanned Aerial Vehicles (UAV) equipped with cameras can play an essential role in speeding up the identification and rescue of people who have fallen overboard, i.e., man overboard (MOB). To this end, Artificial Intelligence techniques can be leveraged for the automatic understanding of visual data acquired from drones. However, detecting people at sea in aerial imagery is challenging primarily due to the lack of specialized annotated datasets for training and testing detectors for this task. To fill this gap, we introduce and publicly release the MOBDrone benchmark, a collection of more than 125K drone-view images in a marine environment under several conditions, such as different altitudes, camera shooting angles, and illumination. We manually annotated more than 180K objects, of which about 113K man overboard, precisely localizing them with bounding boxes. Moreover, we conduct a thorough performance analysis of several state-of-the-art object detectors on the MOBDrone data, serving as baselines for further research.
Source: ICIAP 2022 - 21st International Conference on Image Analysis and Processing, pp. 633–644, Lecce, Italia, 23-27/05/2022
@inproceedings{oai:it.cnr:prodotti:467561, title = {MOBDrone: a drone video dataset for Man OverBoard Rescue}, author = {Cafarelli D. and Ciampi L. and Vadicamo L. and Gennaro C. and Berton A. and Paterni M. and Benvenuti C. and Passera M. and Falchi F.}, doi = {10.1007/978-3-031-06430-2_53}, booktitle = {ICIAP 2022 - 21st International Conference on Image Analysis and Processing, pp. 633–644, Lecce, Italia, 23-27/05/2022}, year = {2022} }
Benvenuti, Chiara
Berton, Andrea
Cafarelli, Donato
0000-0002-7575-0143
Ciampi, Luca
0000-0002-6985-0439
Falchi, Fabrizio
0000-0001-6258-5313
Gennaro, Claudio
0000-0002-3715-149X
Passera, Mirko
Paterni, Marco
Vadicamo, Lucia
0000-0001-7182-7038
Artificial Intelligence for Media and Humanities (2021-ongoing)