Unexploded Ordnance Detection in Hyperspectral Images by Using Deep Neural Networks
Open Access
- 7 March 2025
- conference paper
- Published by University of Maribor
- p. 93-106
Abstract
Unexploded Ordnance (UXO) is a major threat affecting the lives of people in more than 60 countries. This work tests deep neural networks to automatically detect UXO in Hyperspectral Images (HSI). Initially, we constructed our own dataset of 134 HSI cubes divided into three folds: two for training and one for validation. U-Net was selected through preliminary experiments as the most promising detection method among those compared. Customised loss functions were designed for the U-Net, resulting in 3 different models. These models were trained and validated in a supervised manner on our data. The results obtained are very promising with a UXO detection rate of around 70% and an F1 score above 0.8.Keywords
This publication has 8 references indexed in Scilit:
- Spectral Response of Two Hyperspectral Cameras for UXO Endmember Selection2024
- Utilizing UAV-based hyperspectral imaging to detect surficial explosive ordnanceThe Leading Edge, 2023
- Modeling and Simulation of Very High Spatial Resolution UXOs and Landmines in a Hyperspectral Scene for UAV SurveyRemote Sensing, 2021
- The role and the risks of explosive ordnance decontamination in HungaryScience & Military, 2021
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015