A New Fusion Approach for Extracting Urban Built-up Areas from Multisource Remotely Sensed Data

Xiaolong Ma,Xiaohua Tong,Chengming Li,Sicong Liu

doi:10.3390/rs11212516

Xiaolong Ma, Xiaohua Tong + Show 2 more

Open Access

https://doi.org/10.3390/rs11212516

Copy DOI

Abstract

Recent advances in the fusion technology of remotely sensed data have led to an increased availability of extracted urban information from multiple spatial resolutions and multi-temporal acquisitions. Despite the existing extraction methods, there remains the challenging task of fully exploiting the characteristics of multisource remote sensing data, each of which has its own advantages. In this paper, a new fusion approach for accurately extracting urban built-up areas based on the use of multisource remotely sensed data, i.e., the DMSP-OLS nighttime light data, the MODIS land cover product (MCD12Q1) and Landsat 7 ETM+ images, was proposed. The proposed method mainly consists of two components: (1) the multi-level data fusion, including the initial sample selection, unified pixel resolution and feature weighted calculation at the feature level, as well as pixel attribution determination at decision level; and (2) the optimized sample selection with multi-factor constraints, which indicates that an iterative optimization with the normalized difference vegetation index (NDVI), the modified normalized difference water index (MNDWI), and the bare soil index (BSI), along with the sample training of the support vector machine (SVM) and the extraction of urban built-up areas, produces results with high credibility. Nine Chinese provincial capitals along the Silk Road Economic Belt, such as Chengdu, Chongqing, Kunming, Xining, and Nanning, were selected to test the proposed method with data from 2001 to 2010. Compared with the results obtained by the traditional threshold dichotomy and the improved neighborhood focal statistics (NFS) method, the following could be concluded. (1) The proposed approach achieved high accuracy and eliminated natural elements to a great extent while obtaining extraction results very consistent to those of the more precise improved NFS approach at a fine scale. The average overall accuracy (OA) and average Kappa values of the extracted urban built-up areas were 95% and 0.83, respectively. (2) The proposed method not only identified the characteristics of the urban built-up area from the nighttime light data and other daylight images at the feature level but also optimized the samples of the urban built-up area category at the decision level, making it possible to provide valuable information for urban planning, construction, and management with high accuracy.

Highlights

Urban built-up areas are generally defined as the urban administrative region where the majority of the area has been developed, and the municipal public facilities are widely available
This study focused on nine capital cities along the Silk Road Economic Belt in Western China
It can be observed that the green spots in the abovementioned areas are significantly expanded along the outer edges of the built-up areas, shown in red, in 2001, indicating that the urban expansion in the area along the Silk Road Economic Belt is significant in the past decade

Summary

Introduction

Urban built-up areas are generally defined as the urban administrative region where the majority of the area has been developed, and the municipal public facilities are widely available. These areas tend to have a higher population density and more social-environmental problems than their surroundings [1,2]. Labor-intensive and time-consuming disadvantages will become increasingly obvious when considering a large number of scenarios These are the manifestation of the limited usefulness of large-scale studies, especially those predicated on urban remote sensing, such as urban dynamic analysis and geographical condition monitoring

Methods

Results

Conclusion