Abstract
Abstract. A challenge in data-based 3D building reconstruction is to find the exact edges of roof facet polygons. Although these edges are visible in orthoimages, convolution-based edge detectors also find many other edges due to shadows and textures. In this feasibility study, we apply machine learning to solve this problem. Recently, neural networks have been introduced that not only detect edges in images, but also assemble the edges into a graph. When applied to roof reconstruction, the vertices of the dual graph represent the roof facets. In this study, we apply the Point-Pair Graph Network (PPGNet) to orthoimages of buildings and evaluate the quality of the detected edge graphs. The initial results are promising, and adjusting the training parameters further improved the results. However, in some cases, additional work, such as post-processing, is required to reliably find all vertices.
Highlights
3D city models have been reconstructed from airborne laser scanning point clouds
The total loss function is a linear combination of the loss function for Junction Detection Module (JDM) weighted by the factor λjunc, and the loss function for Line Segment Alignment Module (LSAM) and Adjacency Matrix Inference Module (AMIM) weighted by the factor λadj
Compared to other related approaches, the Point-Pair Graph Network (PPGNet) creates a vectorization that is not limited to the footprint of the building
Summary
3D city models have been reconstructed from airborne laser scanning point clouds. In a data-based approach, geometric primitives are detected in the point cloud (for example with a RANSAC algorithm that considers point normals) and are combined. An at least partially data-based approach is necessary to model small structures like dormers and non-standard roofs, for example of churches. Straight lines running through step edges can be estimated only with low precision on sparse point clouds with classical algorithms like RANSAC or the Hough transform. Convolution-based edge detectors find many wrong line segments due to shadows and textures. For this reason, we investigate whether the graph consisting of corners (denoted as junctions) and roof edges can in principle be better recognized by machine learning. We focus on rural areas with clearly sep-
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
