Building roof segmentation in LASER scanning data using image processing techniques and the RANSAC method

• Grant number: 13/16452-8
• Support Opportunities: Scholarships in Brazil - Master
• Effective date (Start): November 01, 2013
• Effective date (End): February 28, 2015
• Field of knowledge: Physical Sciences and Mathematics - Geosciences - Geodesy
• Principal Investigator: Aluir Porfírio Dal Poz
• Grantee: Michelle Sayuri Yano
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil

Abstract

In this project a methodology is proposed for segmentation of buildings roof surfaces present in LASER scanning data, based on image processing techniques and the RANdom Sample Consensus (RANSAC) method. To avoid the simultaneous seek of roof surfaces in the entire LASER's point cloud, initially will be performed a pre-processing of the point cloud to separate the building regions. The separation of building points will be accomplished by the region's delimitation of each building by detection, vectorization and poligonization of the building's contours. This procedure allows the separate analysis of each building, decreasing significantly the computational effort and avoiding the merging of different building segments accidentally coplanar. Posteriorly, the RANSAC method will be used to identify sets of coplanar points belonging to the roof's faces. This method uses a minimum amount of data to determine a hypothetical model (plans, spheres, cylinders), allowing the posterior extension of the initial data sets based on consistency analysis, until the accomplishment of grouping of data's number that ensure the appropriate performance of the hypothetical model. The RANSAC segmentation can produce fragmented results, which also requires a post-processing to the merger of the planar segments spatially close and parallel. This will be performed determining threshold related to the concept of continuity, which involves the proximity and orientation analysis.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DAL POZ, ALUIR PORFIRIO; YANO, MICHELLE SAYURI; IEEE. RANSAC-BASED SEGMENTATION FOR BUILDING ROOF FACE DETECTION IN LiDAR POINT CLOUD. IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, v. N/A, p. 4-pg., 2018-01-01. (13/16452-8)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

YANO, Michelle Sayuri. Segmentação de telhados de edifícios em dados de varredura a LASER usando técnicas de processamento de imagem e o método RANSAC. 2015. Master's Dissertation - Universidade Estadual Paulista (Unesp). Faculdade de Ciências e Tecnologia. Presidente Prudente Presidente Prudente.