Topology-Aware Road Network Extraction via Multi-Supervised Generative Adversarial Networks

Yang Zhang,Xiang Li,Cheng Wang,Zhangyue Xiong,Jonathan Li,Yu Zang

doi:10.3390/rs11091017

Abstract

Road network extraction from remote sensing images has played an important role in various areas. However, due to complex imaging conditions and terrain factors, such as occlusion and shades, it is very challenging to extract road networks with complete topology structures. In this paper, we propose a learning-based road network extraction framework via a Multi-supervised Generative Adversarial Network (MsGAN), which is jointly trained by the spectral and topology features of the road network. Such a design makes the network capable of learning how to “guess” the aberrant road cases, which is caused by occlusion and shadow, based on the relationship between the road region and centerline; thus, it is able to provide a road network with integrated topology. Additionally, we also present a sample quality measurement to efficiently generate a large number of training samples with a little human interaction. Through the experiments on images from various satellites and the comprehensive comparisons to state-of-the-art approaches on the public datasets, it is demonstrated that the proposed method is able to provide high-quality results, especially for the completeness of the road network.

Highlights

Road network extraction is a fundamental issue in remote sensing image processing, which can provide an important reference for road planning or surveys, or prior knowledge for the detection and recognition of vehicles, buildings, or other objects
We propose a topology-aware road network extraction framework via a Multi-supervised Generative Adversarial Network (MsGAN)
We evaluated our method on the Pleiades-1A remote sensing images, which covered an entire city of China (Shaoshan City in Hunan province), in which the reference was obtained by the ground survey and provided by the China Transportation & Telecommunication Center, and presented a comparison with the latest rule-based road network extraction methods

Summary

Introduction

Road network extraction is a fundamental issue in remote sensing image processing, which can provide an important reference for road planning or surveys, or prior knowledge for the detection and recognition of vehicles, buildings, or other objects.Most of the rule-based approaches rely on spectral behavior or intensity contrast [1], relying heavily on appropriate features to describe the “potential road regions” [2,3]. Recent works [3,5,6,7] have tried to reconstruct the road topology via multi-stage schemes according to “assistant information”, such as simple interaction [5], a 3D road surface model [6], pre-defined classifiers [7], or an aperiodic directional structure measurement [3,8] Such rule-based expert systems can fall into a difficult problem—that is, to cover all expected types of roads, they have to exhaustively establish the complex discriminate criterion and at last make it infeasible to tune such expert systems by hand.

Objectives

Methods

Results

Conclusion