Automatic extraction of building geometries based on centroid clustering and contour analysis on oblique images taken by unmanned aerial vehicles. Issue 3 (4th March 2022)

• Record Type: Journal Article
• Authors: Zhang, Leilei; Wang, Guoxin; Sun, Weijian
• Is Part Of: International journal of geographical information science. Volume 36:Issue 3(2022)
• Page Start: 453
• Page End: 475
• Publication Date: 2022-03-04
• Subjects: Building detection -- oblique aerial images -- mean shift clustering -- building geometric information -- unmanned aerial vehicle (UAV); Geography -- Data processing -- Periodicals; Information storage and retrieval systems -- Periodicals; Géomatique -- Périodiques; Systèmes d'information -- Périodiques; 910.285
• DOI: 10.1080/13658816.2021.1937632
• Languages: English
• ISSNs: 1365-8816

Abstract

ABSTRACT: This paper introduces a method based on centroid clustering and contour analysis to extract area and height measurements on buildings from the 3D model generated by oblique images. The method comprises three steps: (1) extract the contour plane from the fused data of the digital surface model (DSM) and digital orthophoto map (DOM); (2) identify building contour clusters based on the number of centroids contained in each category determined by mean-shift centroid clustering; (3) remove the mis-identified contours in a given building contour cluster by a contour analysis and obtain the geometric information of the building using map algebra. The proposed approach was tested against four datasets. Compared with other results, the detection has effective completeness, correctness, quality, and higher geometric accuracy. The maximum average relative error of building height and area extraction is less than 8%. The method is fast for a large-scale collection of building attributes and improves the applicability of oblique photography in GIS.