Automatic 3D Building Detection and Modeling from Airborne LiDAR Point Clouds

Autor/in	Sun, Shaohui
Titel	Automatic 3D Building Detection and Modeling from Airborne LiDAR Point Clouds
Quelle	(2013), (158 Seiten) PDF als Volltext Verfügbarkeit Ph.D. Dissertation, Rochester Institute of Technology
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	978-1-3036-6052-8
Schlagwörter	Hochschulschrift; Dissertation; Automation; Visual Aids; Models; Buildings; Identification; Urban Areas; Information Technology + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Anschauungsmaterial; Analogiemodell; Building; Gebäude; Identifikation; Identifizierung; Urban area; Stadtregion; Informationstechnologie
Abstract	Urban reconstruction, with an emphasis on man-made structure modeling, is an active research area with broad impact on several potential applications. Urban reconstruction combines photogrammetry, remote sensing, computer vision, and computer graphics. Even though there is a huge volume of work that has been done, many problems still remain unsolved. Automation is one of the key focus areas in this research. In this work, a fast, completely automated method to create 3D watertight building models from airborne LiDAR (Light Detection and Ranging) point clouds is presented. The developed method analyzes the scene content and produces multi-layer rooftops, with complex rigorous boundaries and vertical walls, that connect rooftops to the ground. The graph cuts algorithm is used to separate vegetative elements from the rest of the scene content, which is based on the local analysis about the properties of the local implicit surface patch. The ground terrain and building rooftop footprints are then extracted, utilizing the developed strategy, a two-step hierarchical Euclidean clustering. The method presented here adopts a "divide-and-conquer" scheme. Once the building footprints are segmented from the terrain and vegetative areas, the whole scene is divided into individual pendent processing units which represent potential points on the rooftop. For each individual building region, significant features on the rooftop are further detected using a specifically designed region-growing algorithm with surface smoothness constraints. The principal orientation of each building rooftop feature is calculated using a minimum bounding box fitting technique, and is used to guide the refinement of shapes and boundaries of the rooftop parts. Boundaries for all of these features are refined for the purpose of producing strict description. Once the description of the rooftops is achieved, polygonal mesh models are generated by creating surface patches with outlines defined by detected vertices to produce triangulated mesh models. These triangulated mesh models are suitable for many applications, such as 3D mapping, urban planning and augmented reality. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.] (As Provided).
Anmerkungen	ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01