Mechanical, electrical and plumbing (MEP) system provides various services and creates comfortable environments to residents in cities. To enhance the management efficiency of the highly complex MEP system, as-built building information models (BIMs) which can reflect actual conditions of facilities have gained much attention. To create as-built BIMs, reality capture technologies including imaging and laser scanning are widely used to collect raw data. Currently, as-built BIMs are mostly drawn manually by modelers in BIM modeling software referring to on-site photos or point clouds, which is time consuming and labor intensive.

Although research efforts have been made on how to automate “Scan-to-BIM”, there are still gaps from applying current solutions to real MEP scenarios. There are t...[ Read more ]

Mechanical, electrical and plumbing (MEP) system provides various services and creates comfortable environments to residents in cities. To enhance the management efficiency of the highly complex MEP system, as-built building information models (BIMs) which can reflect actual conditions of facilities have gained much attention. To create as-built BIMs, reality capture technologies including imaging and laser scanning are widely used to collect raw data. Currently, as-built BIMs are mostly drawn manually by modelers in BIM modeling software referring to on-site photos or point clouds, which is time consuming and labor intensive.

Although research efforts have been made on how to automate “Scan-to-BIM”, there are still gaps from applying current solutions to real MEP scenarios. There are three major unsolved issues: 1) The degree of automation is low. 2) The applicable MEP component categories are limited. 3) The accuracy of BIM reconstruction is not high enough for industrial applications.

This research aims to develop approaches to automate as-built BIM generation process for MEP systems based on laser scanning and depth camera data with satisfying reconstruction accuracy. In this research, the research objective is achieved with three steps: which are (1) fully automated generation of parametric BIM for MEP scenes based on terrestrial laser scanning data, (2) vision-assisted BIM reconstruction approach for narrowing search scopes, and (3) object verification based on deep learning point feature comparison for Scan-to-BIM.

The first part presents a fully automated approach to converting terrestrial laser scanning data to well-connected as-built BIMs for MEP scenes. According to the geometry complexity, MEP components are divided into regular shaped components and irregular shaped components. A 2D to 3D analysis framework is developed to detect objects and extract accurate geometry information for the two categories of MEP components. Firstly, the MEP scene is divided into slices on which rough geometry information of components' cross sections is extracted. Then, the extracted information on different slices is integrated and analyzed in 3D space to verify the existence of MEP components and obtain refined geometry information used for modeling. Following the detection stage, an MEP network construction approach is developed for MEP components connection and position fine-tuning. Finally, the extracted geometry information and connection relationships are imported into Dynamo to automatically generate the parametric BIM model.

The second part presents a novel fused BIM reconstruction approach for MEP scenes, further improving accuracy and efficiency of the Scan-to-BIM process. The proposed approach makes the best of the rich semantic information provided by images and accurate geometry information provided by 3D LiDAR point clouds. Firstly, a state-of-the-art deep learning model focusing on semantic segmentation is fine-tuned for the MEP dataset, and then RGB images collected with depth camera are segmented with the well-trained model. Secondly, taking the segmented images and the corresponding depth images as input, a semantic-rich 3D map is generated. Thirdly, an instance-aware component extraction algorithm in LiDAR point clouds given approximate object distribution in 3D space is developed. In the component extraction algorithm, a label transfer technique is proposed to firstly determine the rough locations of targeting objects in LiDAR point clouds. Then, accurate component locations are determined for three types of components including irregular shaped components, regular shaped components, and secondary components attached to walls. Finally, the BIM model is reconstructed based on component extraction results.

The third part mainly solves the problem that some irrelevant point clusters may be wrongly recognized as the desired object in the detection stage. As a result, this chapter presents a novel object verification approach based on deep learning point feature comparison to further improve the accuracy of automated BIM reconstruction process. Firstly, a KPConv-based deep neural network is developed and trained to perform 3D point feature computation. Then through comparing point features calculated for extracted point clusters and as-designed BIM generated point clouds, point feature distance maps are generated. Afterwards, to automatically analyze the generated feature distance maps, a dataset including simulated positive and negative instances is created based on ModelNet40. And a tiny neural network is established and trained on the prepared dataset to acquire ability of distinguishment.

To validate the feasibility of the proposed technique, experiments were conducted with point clouds acquired from MEP scenes in Hong Kong. Comprehensive assessments are presented to evaluate the as-built model quality. The experiment results show that the proposed techniques could successfully generate as-built BIMs for MEP scenes for facility management purpose. It is demonstrated that the proposed technique is more accurate and more efficient with wider range of applications compared to previous BIM reconstruction methods.