A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks

Chunping Qiu,Michael Schmitt,Christian Geiß,Tzu-Hsin Karen Chen,Xiao Xiang Zhu

doi:10.1016/j.isprsjprs.2020.01.028

Chunping Qiu, Michael Schmitt + Show 3 more

Open Access

https://doi.org/10.1016/j.isprsjprs.2020.01.028

Copy DOI

Abstract

Human settlement extent (HSE) information is a valuable indicator of world-wide urbanization as well as the resulting human pressure on the natural environment. Therefore, mapping HSE is critical for various environmental issues at local, regional, and even global scales. This paper presents a deep-learning-based framework to automatically map HSE from multi-spectral Sentinel-2 data using regionally available geo-products as training labels. A straightforward, simple, yet effective fully convolutional network-based architecture, Sen2HSE, is implemented as an example for semantic segmentation within the framework. The framework is validated against both manually labelled checking points distributed evenly over the test areas, and the OpenStreetMap building layer. The HSE mapping results were extensively compared to several baseline products in order to thoroughly evaluate the effectiveness of the proposed HSE mapping framework. The HSE mapping power is consistently demonstrated over 10 representative areas across the world. We also present one regional-scale and one country-wide HSE mapping example from our framework to show the potential for upscaling. The results of this study contribute to the generalization of the applicability of CNN-based approaches for large-scale urban mapping to cases where no up-to-date and accurate ground truth is available, as well as the subsequent monitor of global urbanization.

Highlights

Human settlement extent (HSE), which is characterized by buildings, roads, and other man-made structures, is an essential indicator of the human footprint on the Earth
We propose a framework for large-scale HSE mapping from Sentinel-2 imagery using deep learning-based approaches with three major parts: (1) preparation of labels and image data, (2) training a well-generalizing semantic segmentation network to learn to map HSE from Sentinel-2 images (Sen2HSE-Net), and (3) a statistically sound accuracy assessment of the HSE results
We are able to achieve state-of-the-art HSE results for several representative scenes across the world

Summary

Introduction

Human settlement extent (HSE), which is characterized by buildings, roads, and other man-made structures, is an essential indicator of the human footprint on the Earth. It is an expression of the impact of ongoing worldwide urbanization. Recent years have seen a proliferation of studies related to HSE mapping, among which remote sensing-based approaches have gained more and more attention due to their inherent ability to frequently and regularly observe the land surface on a global scale. With this unique property, several remote sensing-based global products related to HSE have become available. The Global Urban Footprint (GUF), was derived using TerraSAR-X as well as TanDEM-X Synthetic Aperture

Objectives

Methods

Findings

Discussion

Conclusion