This work presents an application to drone technology based on an algorithm which combines a convolutional neural network (CNN) and a symbolic data analysis (SDA) process to detect anti-personnel mines from GPR data acquisitions. The CNN is aimed at automatically detecting buried objects; the SDA reduces the probability of objects identified as mines, even though they are not.
Mine clearance through an artificial intelligence flying drone / Mezzani, Federica; Pepe, Gianluca; Roveri, Nicola; Carcaterra, Antonio. - (2022), pp. 417-426. (Intervento presentato al convegno Proceedings of the Second International Nonlinear Dynamics Conference (NODYCON 2021) tenutosi a Rome, Italy) [10.1007/978-3-030-81166-2_37].
Mine clearance through an artificial intelligence flying drone
Federica Mezzani
;Gianluca Pepe;Nicola Roveri;Antonio Carcaterra
2022
Abstract
This work presents an application to drone technology based on an algorithm which combines a convolutional neural network (CNN) and a symbolic data analysis (SDA) process to detect anti-personnel mines from GPR data acquisitions. The CNN is aimed at automatically detecting buried objects; the SDA reduces the probability of objects identified as mines, even though they are not.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
