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

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.

References in corpus (15)

• Deep learning in remote sensing: a review
• An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing
• Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data
• BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding
• Dense semantic labeling of sub-decimeter resolution images with convolutional neural networks
• Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders
• Learnable Manifold Alignment (LeMA) : A Semi-supervised Cross-modality Learning Framework for Land Cover and Land Use Classification
• CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences
• Country-wide high-resolution vegetation height mapping with Sentinel-2
• Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification
• Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
• So2Sat LCZ42: A Benchmark Dataset for Global Local Climate Zones Classification
• Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery
• Towards Automatic SAR-Optical Stereogrammetry over Urban Areas using Very High Resolution Imagery
• Multisource and Multitemporal Data Fusion in Remote Sensing

Cited by in corpus (5)

• Convolutional Neural Networks for Global Human Settlements Mapping from Sentinel-2 Satellite Imagery
• Mapping horizontal and vertical urban densification in Denmark with Landsat time-series from 1985 to 2018: a semantic segmentation solution
• MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
• Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset
• Multi-task Learning for Human Settlement Extent Regression and Local Climate Zone Classification