Building Extraction from High-Resolution Remote Sensing Images by Adaptive Morphological Attribute Profile under Object Boundary Constraint.

Chao Wang,Xing Qiu,Kaiguang Zhao,Hui Liu,Yi Shen,Hongyan Xing

doi:10.3390/s19173737

Abstract

A novel adaptive morphological attribute profile under object boundary constraint (AMAP–OBC) method is proposed in this study for automatic building extraction from high-resolution remote sensing (HRRS) images. By investigating the associated attributes in morphological attribute profiles (MAPs), the proposed method establishes corresponding relationships between AMAP–OBC and building characteristics in HRRS images. In the preprocessing step, the candidate object set is extracted by a group of rules for screening of non-building objects. Second, based on the proposed adaptive scale parameter extraction and object boundary constraint strategies, AMAP–OBC is conducted to obtain the initial building set. Finally, a further identification strategy with adaptive threshold combination is proposed to obtain the final building extraction results. Through experiments of multiple groups of HRRS images from different sensors, the proposed method shows outstanding performance in terms of automatic building extraction from diverse geographic objects in urban scenes.

Highlights

With the continuous improvement of satellite and sensor technology, high–resolution remote sensing (HRRS) images have been widely used in many fields, such as updating geographic databases, creating urban thematic maps, etc
This study mainly includes six sections: Section 2 contains the analysis of building characteristics in high-resolution remote sensing images; in Section 3, we briefly describe the morphological attribute profiles (MAPs) theory and constitution of the building attribute set; in Section 4, we elaborate on the implementation steps of the proposed method; Section 5 contains an analysis and discussion of the experiments; and in Section 6, we give the conclusion
By establishing the corresponding relationships between AMAP–OBC and characteristics of buildings in HRRS images, a set of scale parameters could be adaptively obtained, and the connected area extraction was restricted by the inherent boundaries of geographic objects

Summary

Introduction

With the continuous improvement of satellite and sensor technology, high–resolution remote sensing (HRRS) images have been widely used in many fields, such as updating geographic databases, creating urban thematic maps, etc. As buildings are among the most representative types of artificial targets in urban scenes, extraction of buildings from HRRS images is important in these applications [1,2,3]. Compared with traditional medium- and low-resolution remote sensing images, a great amount of semantic, textural, and spatial information of land covers is contained in HRRS images. The increasing resolution of remote sensing images leads to the prominent phenomena of high intraclass variance and low interclass variance, which reduce the ability to distinguish buildings and other geographic objects [4]. Machine learning-based methods are the main strategy for building a feature extraction [8,9,10,11]

Methods

Discussion

Conclusion