Super-Resolution Mapping of Impervious Surfaces from Remotely Sensed Imagery with Points-of-Interest

Yuehong Chen,Ru An,Yong Ge,Yu Chen

doi:10.3390/rs10020242

Abstract

The accurate mapping of impervious surfaces is of key significance for various urban applications. Usually, traditional methods extract the proportion image of impervious surfaces from remote sensing images; however, the proportion image cannot specify where the impervious surfaces spatially distribute within a pixel. Meanwhile, impervious surfaces often locate urban areas and have a strong correlation with the relatively new big (geo)data points of interest (POIs). This study, therefore, proposed a novel impervious surfaces mapping method (super-resolution mapping of impervious surfaces, SRMIS) by combining a super-resolution mapping technique and POIs to increase the spatial resolution of impervious surfaces in proportion images and determine the accurate spatial location of impervious surfaces within each pixel. SRMIS was evaluated using a 10-m Sentinel-2 image and a 30-m Landsat 8 Operational Land Imager (OLI) image of Nanjing city, China. The experimental results show that SRMIS generated satisfactory impervious surface maps with better-classified image quality and greater accuracy than a traditional hard classifier, the two existing super-resolution mapping (SRM) methods of the subpixel-swapping algorithm, or the method using both pixel-level and subpixel-level spatial dependence. The experimental results show that the overall accuracy increase of SRMIS was from 2.34% to 5.59% compared with the hard classification method and the two SRM methods in the first experiment, while the overall accuracy of SRMIS was 1.34–3.09% greater than that of the compared methods in the second experiment. Hence, this study provides a useful solution to combining SRM techniques and the relatively new big (geo)data (i.e., POIs) to extract impervious surface maps with a higher spatial resolution than that of the input remote sensing images, and thereby supports urban research.

Highlights

Impervious surfaces are mainly artificial areas where water cannot infiltrate the soil [1,2]
The extraction of impervious surfaces from remote sensing imagery still suffers from several issues: (1) the accuracy of impervious surfaces is limited by the complexity of impervious surfaces because impervious surfaces are mainly distributed in complicated urban areas [9]; (2) mixed pixels composed of impervious surfaces and other land features are inevitable in various spatial resolution images [6,10]; (3) impervious surfaces from low and medium spatial resolution images are often too coarse to use in urban environments [1]; and (4) most impervious surface maps can provide the proportion of impervious surfaces by soft classification but cannot specify where impervious surfaces are spatially distributed within pixels [11,12,13]
For the mixed pixel problem, an attractive solution is the super-resolution mapping (SRM) technique [15]. It first increases the spatial resolution of each pixel in the proportion images derived from a soft classification and determines the spatial location of classes within each pixel [16,17,18,19,20]

Summary

Introduction

Impervious surfaces are mainly artificial areas where water cannot infiltrate the soil [1,2]. There have been three main approaches to mapping impervious surfaces: (1) pixel-based (i.e., hard classification), (2) subpixel-based (i.e., soft classification or spectral unmixing), and (3) object-based algorithms [1] These approaches have been applied to various remote sensing images including low spatial resolution (>100 m), medium spatial resolution (10–100 m), and high spatial resolution (

Objectives

Methods

Findings

Discussion

Conclusion