Context-Enabled Extraction of Large-Scale Urban Functional Zones from Very-High-Resolution Images: A Multiscale Segmentation Approach

Shouji Du,Shihong Du,Xiuyuan Zhang,Bo Liu

doi:10.3390/rs11161902

Abstract

Urban functional-zone (UFZ) analysis has been widely used in many applications, including urban environment evaluation, and urban planning and management. How to extract UFZs’ spatial units which delineates UFZs’ boundaries is fundamental to urban applications, but it is still unresolved. In this study, an automatic, context-enabled multiscale image segmentation method is proposed for extracting spatial units of UFZs from very-high-resolution satellite images. First, a window independent context feature is calculated to measure context information in the form of geographic nearest-neighbor distance from a pixel to different image classes. Second, a scale-adaptive approach is proposed to determine appropriate scales for each UFZ in terms of its context information and generate the initial UFZs. Finally, the graph cuts algorithm is improved to optimize the initial UFZs. Two datasets including WorldView-2 image in Beijing and GaoFen-2 image in Nanchang are used to evaluate the proposed method. The results indicate that the proposed method can generate better results from very-high-resolution satellite images than widely used approaches like image tiles and road blocks in representing UFZs. In addition, the proposed method outperforms existing methods in both segmentation quality and running time. Therefore, the proposed method appears to be promising and practical for segmenting large-scale UFZs.

Highlights

Urban socioeconomic activities demonstrate strong clustering patterns in space, leading to the generation of various urban functional zones (UFZs) to accommodate people’s diverse needs for living, working, education, recreation, and public service [1,2]
To evaluate the effectiveness of the proposed UFZ segmentation method, a study area located in Beijing was used to perform the experiments (Figure 5) and it covered approximately 36 km2
UFZs are the basis of urban planning and play an important role in monitoring urbanization

Summary

Introduction

Urban socioeconomic activities demonstrate strong clustering patterns in space, leading to the generation of various urban functional zones (UFZs) to accommodate people’s diverse needs for living, working, education, recreation, and public service [1,2]. UFZs act as an important space carrier to implement urban economic and social functions, they are typically employed as the basic units in urban planning and management [3,4,5]. There are two issues challenging the production of an accurate functional-zone map: how to generate the spatial units of UFZs? Recent advancement in analyzing very-high-resolution (VHR) remote sensing provides an alternative to generate the spatial units of UFZs, which takes advantage of the spectral and Remote Sens. Recent advancement in analyzing very-high-resolution (VHR) remote sensing provides an alternative to generate the spatial units of UFZs, which takes advantage of the spectral and Remote Sens. 2019, 11, 1902; doi:10.3390/rs11161902 www.mdpi.com/journal/remotesensing

Methods

Results

Discussion

Conclusion