Deep Learning-Based Real-Time Detection of Surface Landmines Using Optical Imaging
Open Access
- 14 February 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (4) , 677
Abstract
This paper presents a pioneering study in the application of real-time surface landmine detection using a combination of robotics and deep learning. We introduce a novel system integrated within a demining robot, capable of detecting landmines in real time with high recall. Utilizing YOLOv8 models, we leverage both optical imaging and artificial intelligence to identify two common types of surface landmines: PFM-1 (butterfly) and PMA-2 (starfish with tripwire). Our system runs at 2 FPS on a mobile device missing at most 1.6% of targets. It demonstrates significant advancements in operational speed and autonomy, surpassing conventional methods while being compatible with other approaches like UAV. In addition to the proposed system, we release two datasets with remarkable differences in landmine and background colors, built to train and test the model performances.Keywords
Funding Information
- ASMARA, Tuscany Regional (G5731)
- NATO-SPS (G5731)
This publication has 43 references indexed in Scilit:
- Dataset of thermographic images for the detection of buried landminesData in Brief, 2023
- A comprehensive review on landmine detection using deep learning techniques in 5G environment: open issues and challengesNeural Computing and Applications, 2022
- 3D Object Detection for Autonomous Driving: A SurveyPattern Recognition, 2022
- A Survey on Deep Learning Approaches to Medical Images and a Systematic Look up into Real-Time Object DetectionArchives of Computational Methods in Engineering, 2021
- A combined strategy for landmine detection and identification using synthetic GPR responsesJournal of Applied Geophysics, 2013
- Soil properties and performance of landmine detection by metal detector and ground-penetrating radar — Soil characterisation and its verification by a field testJournal of Applied Geophysics, 2011
- Anti-personnel Landmine Detection for Humanitarian Demining2009
- Augmented Vision Perception in Infrared2009
- Unexploded Ordnance Detection and Mitigation2009
- Mine detection by means of dynamic thermography: simulation and experiments1998