Building Change Detection Using a Shape Context Similarity Model for LiDAR Data

Xuzhe Lyu,Wenzhong Shi,Ming Hao

doi:10.3390/ijgi9110678

Abstract

In this paper, a novel building change detection approach is proposed using statistical region merging (SRM) and a shape context similarity model for Light Detection and Ranging (LiDAR) data. First, digital surface models (DSMs) are generated from LiDAR acquired at two different epochs, and the difference data D-DSM is created by difference processing. Second, to reduce the noise and registration error of the pixel-based method, the SRM algorithm is applied to segment the D-DSM, and multi-scale segmentation results are obtained under different scale values. Then, the shape context similarity model is used to calculate the shape similarity between the segmented objects and the buildings. Finally, the refined building change map is produced by the k-means clustering method based on shape context similarity and area-to-length ratio. The experimental results indicated that the proposed method could effectively improve the accuracy of building change detection compared with some popular change detection methods.

Highlights

Building change detection from remote sensing data is an important technology in land cover change, disaster assessment, and city monitoring [1,2,3]
When Q was too small, only the basic objects in the difference digital surface models (DSMs) data could be segmented into complete parts, and the generated segmentation result was too coarse, which resulted in more missed detection errors
For high-rise buildings, the changes caused by registration errors can be detected, which reduces the accuracy of the building change detection results

Summary

Introduction

Building change detection from remote sensing data is an important technology in land cover change, disaster assessment, and city monitoring [1,2,3]. Buildings constitute the main component of a city, and the building extraction and building change detection remain challenging tasks due to the complexity of urban scenes [4]. Over the past few years, a series of automatic building change detection methods have been developed from remote sensing data. The state-of-the-art methods based on images still face the following major challenges: (1) occlusion and shadows between buildings; (2) being affected by factors such as seasons and registration accuracy; (3) difficulty to distinguish buildings from other man-made constructions, such as roads; (4) lack of height information, which limits the development of three-dimensional building change detection [6]

Methods

Results

Conclusion