Abstract
A 3D building model retrieval method using airborne LiDAR point clouds as input queries is introduced. Based on the concept of data reuse, available building models in the Internet that have geometric shapes similar to a user-specified point cloud query are retrieved and reused for the purpose of data extraction and building modeling. To retrieve models efficiently, point cloud queries and building models are consistently and compactly encoded by the proposed method. The encoding focuses on the geometries of building roofs, which are the most informative part of a building in airborne LiDAR acquisitions. Spatial histograms of geometric features that describe shapes of building roofs are utilized as shape descriptor, which introduces the properties of shape distinguishability, encoding compactness, rotation invariance, and noise insensitivity. These properties facilitate the feasibility of the proposed approaches for efficient and accurate model retrieval. Analyses on LiDAR data and building model databases and the implementation of web-based retrieval system, which is available at http://pcretrieval.dgl.xyz, demonstrate the feasibility of the proposed method to retrieve polygon models using point clouds.
Highlights
Recent development on 3D scanning and modeling technologies has led to an increasing number of 3D models, and most of the models have been made available in web-based platforms with data-sharing service
The original model with hollow geometry, which is denoted by LoD1a, is gradually reduced to a non-hollow model with simplified roof geometry, which is denoted as LoD4a
The results indicate that the proposed encoding method can separate the model with hollow geometry from the model without hollow geometry
Summary
Recent development on 3D scanning and modeling technologies has led to an increasing number of 3D models, and most of the models have been made available in web-based platforms with data-sharing service In this context, the question of “How to generate 3D building models?” may evolve to “How to find them in model databases and in the Internet?” [1]. The naive approach called text-based retrieval uses keywords in metadata to search for the desired 3D models This method is simple and efficient, but using keywords as queries suffers from difficulties caused by inappropriate annotations and language varieties. Most previous studies on content-based 3D model retrieval take polygon models as input queries [6,7] These methods can efficiently and accurately extract models from databases. Based on the concepts of data reuse and crowsourcing, the proposed system can efficiently construct a 3D city model which is one of key components in virtual geographic environment
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have