Machine learning has proven to be useful in classification and segmentation of images. In this paper, we evaluate a training methodology for pixel-wise segmentation on high resolution satellite images using progressive growing of generative adversarial networks. We apply our model to segmenting building rooftops and compare these results to conventional methods for rooftop segmentation. We present our findings using the SpaceNet version 2 dataset. Progressive GAN training achieved a test accuracy of 93% compared to 89% for traditional GAN training.
@article{arxiv.1902.04604,
title = {Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images},
author = {Edward Collier and Kate Duffy and Sangram Ganguly and Geri Madanguit and Subodh Kalia and Gayaka Shreekant and Ramakrishna Nemani and Andrew Michaelis and Shuang Li and Auroop Ganguly and Supratik Mukhopadhyay},
journal= {arXiv preprint arXiv:1902.04604},
year = {2019}
}
Comments
Accepted too and presented at DMESS 2018 as part of IEEE ICDM 2018