A Novel Adaptive Deep Network for Building Footprint Segmentation

TL;DR

This paper introduces a novel deep learning network based on Pix2Pix, called G2G, designed to improve the accuracy of building footprint segmentation in satellite images by better capturing object boundaries.

Contribution

The paper proposes a new dual-generator network architecture that enhances boundary detection in building footprint segmentation, outperforming existing state-of-the-art methods.

Findings

Outperforms state-of-the-art segmentation networks in accuracy

Effectively captures detailed building edges

Uses dual-generator architecture for improved boundary delineation

Abstract

Building footprint segmentations for high resolution images are increasingly demanded for many remote sensing applications. By the emerging deep learning approaches, segmentation networks have made significant advances in the semantic segmentation of objects. However, these advances and the increased access to satellite images require the generation of accurate object boundaries in satellite images. In the current paper, we propose a novel network-based on Pix2Pix methodology to solve the problem of inaccurate boundaries obtained by converting satellite images into maps using segmentation networks in order to segment building footprints. To define the new network named G2G, our framework includes two generators where the first generator extracts localization features in order to merge them with the boundary features extracted from the second generator to segment all detailed building edges. Moreover, different strategies are implemented to enhance the quality of the proposed networks' results, implying that the proposed network outperforms state-of-the-art networks in segmentation accuracy with a large margin for all evaluation metrics. The implementation is available at https://github.com/A2Amir/A-Novel-Adaptive-Deep-Network-for-Building-Footprint-Segmentation.