Abstract
Automated reconstruction of Building Information Models (BIMs) from point clouds has been an intensive and challenging research topic for decades. Traditionally, 3D models of indoor environments are reconstructed purely by data-driven methods, which are susceptible to erroneous and incomplete data. Procedural-based methods such as the shape grammar are more robust to uncertainty and incompleteness of the data as they exploit the regularity and repetition of structural elements and architectural design principles in the reconstruction. Nevertheless, these methods are often limited to simple architectural styles: the so-called Manhattan design. In this paper, we propose a new method based on a combination of a shape grammar and a data-driven process for procedural modelling of indoor environments from a point cloud. The core idea behind the integration is to apply a stochastic process based on reversible jump Markov Chain Monte Carlo (rjMCMC) to guide the automated application of grammar rules in the derivation of a 3D indoor model. Experiments on synthetic and real data sets show the applicability of the method to efficiently generate 3D indoor models of both Manhattan and non-Manhattan environments with high accuracy, completeness, and correctness.
Highlights
Automatic reconstruction of 3D indoor models is of great interest in photogrammetry, computer vision, and computer graphics, owing to its wide range of applications in construction management, emergency response, and location-based services [1,2]
We propose a new method based on the combination of a shape grammar and a data-driven process which can overcome the limitation of each strategy to procedurally reconstruct 3D models of indoor environments from lidar point clouds
In this paper, we focus on the reconstruction of 3D indoor models from point clouds
Summary
Automatic reconstruction of 3D indoor models is of great interest in photogrammetry, computer vision, and computer graphics, owing to its wide range of applications in construction management, emergency response, and location-based services [1,2]. Numerous approaches for automated generation of 3D indoor models using imagery or lidar data have been employed Often, these approaches extract 3D geometries of buildings based purely on a data-driven process, which heavily depend on the quality of the data [6,7,8]. In comparison with the data-driven approaches, this procedural-based strategy is less sensitive to erroneous and incomplete data It requires a set of grammar rules, and in the existing grammar-based approaches to indoor modelling, the parameters and application order of the rules are manually predefined. These approaches are applicable only to simple grid-like architectural designs known as Manhattan world [11,15]
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 callDisclaimer: 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.
