Road Extraction by Deep Residual U-Net

TL;DR

This paper introduces a deep residual U-Net model for road extraction from aerial images, combining residual learning and U-Net architecture to improve training efficiency and segmentation accuracy, outperforming existing methods.

Contribution

The paper proposes a novel residual U-Net architecture that enhances deep network training and information propagation for improved road extraction performance.

Findings

Outperforms U-Net and other state-of-the-art methods on a public road dataset.

Residual units facilitate training of deeper networks.

Rich skip connections improve information flow and segmentation accuracy.

Abstract

Road extraction from aerial images has been a hot research topic in the field of remote sensing image analysis. In this letter, a semantic segmentation neural network which combines the strengths of residual learning and U-Net is proposed for road area extraction. The network is built with residual units and has similar architecture to that of U-Net. The benefits of this model is two-fold: first, residual units ease training of deep networks. Second, the rich skip connections within the network could facilitate information propagation, allowing us to design networks with fewer parameters however better performance. We test our network on a public road dataset and compare it with U-Net and other two state of the art deep learning based road extraction methods. The proposed approach outperforms all the comparing methods, which demonstrates its superiority over recently developed state of the arts.