Classification of UXO Using Convolutional Networks Trained on a Limited Dataset

Classification of unexploded ordnance (UXO) in a fast and accurate manner is an imperative need in both the military and humanitarian demining contexts. An automated algorithm would significantly make the task safer, more convenient and less expensive. This paper targets this problem with the development of an image based approach and employs convolutional networks with images that were acquired on a custom camera setup. As access to multiple samples of ordnance can often be an issue, this work focuses on training the algorithm using a limited dataset and for optimizing its performance when ordnance is found in varying conditions. In particular, seven classes of UXO are considered with 420 images used for the training set and 140 images for the validation set. Using images that account for variation, a classifier was developed which was found to be 97.1% accurate.