Efficient workflow transforming large 3D point clouds to Building Information Models with user-assisted automatization

Project description:

Initial situation and problem statement: On average, a large construction site exceeds the original cost framework by 80% and takes 20% longer than planned. Digital tech-nologies promise to overcome this unsatisfactory situation in architecture, engineering and construction (AEC). In fact, by now 3D scanners and Building Information Model (BIMs) have become common on large construction sites and in building maintenance as flexible, cooperative-creative digital eco-systems.
With the rapid progress of 3D measurement technology, 3D scanners deliver more accurate and high-resolution 3D point clouds than ever before. The automated transformation of these datasets, com-prising several hundred million 3D points, to the virtual BIM reality is still an unsolved problem though. Time-consuming pre-processing steps, the lack of tools for the merg-ing of 3D recordings, various time-, cost- and error-intensive manual steps, as well as lack of user-friendly interfaces are the main challenges.

Goals and degree of innovation: The objectives of the proposed project are research and human-centred design of a new efficient workflow for an as-automated-as-possible transformation of huge, unorganized, raw 3D point clouds into BIMs. With an interdisciplinary team and with the active involvement of future users, LargeClouds2BIM develops algorithms and data structures for the progressive real-time visualization of massive point clouds, which allow the users to work on such data without any noticeable pre-processing time.
The robust and precise registration of multiple 3D point clouds with similarity transformations makes data capturing more independent from specific 3D scanner technologies. Through linking minimal user input with powerful optimization methods from geometry processing, the project aims at a novel approach in user-guided reconstruction of BIM objects from 3D point clouds. The exploration of flexible and active interfaces to open and proprietary BIM ecosystems represents the last innovative sub-goal of the proposed project.

Aimed results and insights: At the system level, the project aims for research and (at lab-scale) the conceptual proof of the proposed innovative workflow for the transformation of huge 3D point clouds to BIMs. At the component level, the interdisciplinary project team works out theoretical concepts and prototypical implementation of algorithms and data structures for the progressive real-time visualization, similarity trans-forming registration, as-automated-as-possible reconstruction of BIM objects as well as user-friendly, active interfaces to open and proprietary BIM ecosystems.
The final evaluation of the entire workflow analyses how far the improved automation, flexibility and degree of accuracy may exploit the expected cost and time savings of an estimated 20-30%.