SBIR Phase II: Automatic Generation of As-Built BIM Models Using a Single Video Camera

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project will be to transform commercial construction through the democratization of scanning and automation of Building Information Modeling (BIM). Constant design and change management is a unique challenge that is costing the US construction industry billions of dollars annually. In order to prevent such a huge economic loss, this industry is in the path for a digital revolution. BIM is known as the first truly global digital technology that could revolutionize the construction industry. However, BIM usage is currently limited because it is only viable for large-scale projects. The primary reason is that the process is too laborious and expensive. The proposed technology will completely eliminate these barriers. Its ease-of-use, ubiquity of the capturing device, and automated object detection democratizes as-built BIM modeling. Enormous value could be generated due to streamlining and data management capabilities that are offered by the technology in the form of accelerated project schedules, reduced numbers of requests for information and change orders, and timely identified design clashes. This will pave the way to increase the competitiveness of the US construction industry, by enabling new products and services that support automatic BIM modeling. This Small Business Innovation Research (SBIR) Phase II project investigates the technical and commercial feasibility of an automatic and inexpensive solution for the Scan-to-BIM problem in the construction industry. Scan-to-BIM refers to 3D scanning of a physical structure and converting the captured raw spatial data into an object-oriented, semantically-rich model. Although there are a few technologies that aim to facilitate this process, the 3D modeling component remains primarily a manual and time-consuming task. When using the proposed technology, a non-technical worker videotapes the target structure. The video is automatically sent to a server for processing. A unique videogrammetric 3D reconstruction engine reconstructs the 3D geometry of the structure in the form of a 3D point cloud. It then extracts object hypotheses from key video frames and spatial data in the form of observations. Afterwards, it optimizes a novel coherent joint probability distribution function and infers a 3D layout. The outcome is an object-oriented 3D representation of the structure with embedded geometrical attributes and property sets. The main novelty of this technology lies in a hybrid approach that combines low-level segmentation with high-level space modeling. This advances the state-of-the-art in robust intelligence, particularly the interpretation of complex, unstructured data.