I-Corps: Automated As-is Facade Modeling of High-rise Buildings Using Drones and Artificial Intelligence

Award ID: 2224104

The broader impact/commercial potential of this I-Corps project is the development of a high-rise building faade inspection technology. The new techology is based on the development of an automated, high-rise building faade modeling technology that uses drones and artificial intelligence (AI) algorithms. The application has financial promise because it addresses the deterioration of building infrastructure. The proposed project may improve building inspection, maintenance, renovation, and repair while also educating and training the next generation of skilled workers. This I-Corps project is based on the development of an automated, as-is, high-rise building faade modeling technology using drones and artificial intelligence (AI) algorithms. To begin, a drone with a spiral path is employed to capture building exterior images and photogrammetry is used to conduct 3D reconstructions and create mesh models for the scanned building faades. High-resolution faade orthoimages are generated from mesh models and pixelwise segmented by an AI model. A combined data augmentation strategy, including random flipping, rotation, resizing, perspective transformation and color adjustment, is utilized for model training with few labels. The developed technology may transform the way that high-rise building faades will be inspected. Missing faade drawings may be reproduced for maintenance, renovation, and repair operations. This technology may improve communication among building owners, design firms, contractors, material suppliers, and financial institutions while speeding up the design, approval, finance, construction and inspection processes. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Molly Wasko