Building Detection From Satellite Imagery Using a Composite Loss Function

Sergey Golovanov, Rauf Kurbanov, Aleksey Artamonov, Alex Davydow, Sergey Nikolenko; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 229-232

Abstract

In this paper, we present a LinkNet-based architecture with SE-ResNeXt-50 encoder and a novel training strategy that strongly relies on image preprocessing and incorporating distorted network outputs. The architecture combines a pre-trained convolutional encoder and a symmetric expanding path that enables precise localization. We show that such a network can be trained on plain RGB images with a composite loss function and achieves competitive results on the DeepGlobe challenge on building extraction from satellite images.

Related Material

[pdf]
[bibtex]
@InProceedings{Golovanov_2018_CVPR_Workshops,
author = {Golovanov, Sergey and Kurbanov, Rauf and Artamonov, Aleksey and Davydow, Alex and Nikolenko, Sergey},
title = {Building Detection From Satellite Imagery Using a Composite Loss Function},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}