A method for automatic identification of openings in buildings facades based on mobile LiDAR point clouds for assessing impacts of floodings

• Published in: International journal of applied earth observation and geoinformation Vol. 108; p. 102757
• Main Authors: Haghighatgou, Niloufar, Daniel, Sylvie, Badard, Thierry
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2022
• Subjects: data collection; decision making; inventories; lidar; Mobile LiDAR point cloud; Opening detection; Quebec; Region growing segmentation; risk assessment; Rural building; spatial data; statistics; Quebec; Mobile LiDAR point cloud; Rural building; Region growing segmentation; Opening detection
• DOI: 10.1016/j.jag.2022.102757
• ISSN: 1569-8432

•An opening detection approach dedicated to houses in rural context without repetitive pattern.•A region growing method adaptive to point density to extract simple to complex facade.•Inventory of frequent opening detection challenges in mobile LiDAR point cloud. Given the high frequency and major impact of flood events, decision-makers are in urgent need to have tools allowing them to predict or assess the impact of flood events on the population, such as flood simulation through digital 3D cities. While building’s lowest openings are more subject to potential damages during the flood, 3D building models of rural environments still lack this information. Thus, it would be required to provide the location of the building lowest openings, in the context of flood risk assessment. Unlike frequently developed methods in opening detection domain that benefit from the repetitive structure and symmetrical characterization of the openings on the facades of modern buildings in urban areas, this paper proposed a comprehensive approach that investigates low-rise residential houses of rural areas where openings have various shapes, sizes, and non-symmetrical positions on the facade. First, it proposed a generalized segmentation approach in a context involving various and complex facade structures, in the presence of frequent occlusion and noticeable point density changes. Second, it proposed a simple and consistent hole-based opening detection by effective elimination of window crossbars and curtains. Finally, by proposing an inventory of frequent challenges related to facade extraction and opening detection tasks, it enables a better understanding of the difficulties to help in providing more efficient and relevant solutions in rural residential contexts. Qualitative and quantitative evaluations were performed using an MLS real-world dataset of the Quebec Province, Canada. Related statistics revealed that the proposed approach could obtain good performance rates despite the complexity of the dataset, representative of the data acquired in real situations. Challenges regarding the characteristics of the MLS point cloud and the presence of large surrounding occlusions should be further investigated for obtaining more accurate opening information on the facade.