Date of Award

9-3-2019

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

Yuan, X.

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

Along with the ever-increasing popularity of virtual reality technology in recent years, 3D city models have been used in different applications, such as urban planning, disaster management, tourism, entertainment, and video games. Currently, those models are mainly reconstructed from access-restricted data sources such as LiDAR point clouds, airborne images, satellite images, and UAV (uncrewed air vehicle) images with a focus on structural illustration of buildings’ contours and layouts. To help make 3D models closer to their real-life counterparts, this thesis research proposes a new approach for the automatic reconstruction of building models from open resources. In this approach, first, building shapes are reconstructed by using the structural and geographic information retrievable from the open repository of OpenStreetMap (OSM). Later, images available from the street view of Google maps are used to extract information of the exterior appearance of buildings for texture mapping onto their boundaries. The constructed 3D environment is used as prior knowledge for the navigation purposes in a self-driving car. The static objects from the 3D model are compared with the real-time images of static objects to reduce the computation time by eliminating them from the detection process

Share

COinS