This study uses the challenging and publicly available SpaceNet dataset to establish a performance baseline for a state-of-the-art object detector in satellite imagery. Specifically, we examine how various features of the data affect building detection accuracy with respect to the Intersection over Union metric. We demonstrate that the performance of the R-FCN detection algorithm on imagery with a 1.5 meter ground sample distance and three spectral bands increases by over 32% by using 13-bit data, as opposed to 8-bit data at the same spatial and spectral resolution. We also establish accuracy trends with respect to building size and scene density. Finally, we propose and evaluate multiple methods for integrating additional spectral information into off-the-shelf deep learning architectures. Interestingly, our methods are robust to the choice of spectral bands and we note no significant performance improvement when adding additional bands.
@article{arxiv.1808.02443,
title = {Overhead Detection: Beyond 8-bits and RGB},
author = {Eliza Mace and Keith Manville and Monica Barbu-McInnis and Michael Laielli and Matthew Klaric and Samuel Dooley},
journal= {arXiv preprint arXiv:1808.02443},
year = {2018}
}