Ph.D. researchers and assistant professor, Tarek Rakha, flying a drone in the Hinman Courtyard.

Aerial Diagnostics

Aerial Diagnostics

The Aerial Diagnostics group focuses on the use of Unmanned Aerial Vehicles (UAVs) for analytical applications in the built environment. We utilize the unparalleled vantage points drones offer to explore novel ways of surveying buildings and diagnosing anomalies with a myriad of different drone-borne sensors. Research within the group goes beyond the practical application of drones and transcends into synthesizing computational solutions based on Machine Learning (ML) and Computer Vision (CV) techniques to automate and streamline surveying and diagnostics tasks and data gathering processes.

Using the High Performance Building Lab’s drone fleet, varying in sizes and payloads, the group has utilized this technology in various capacities. We employ drones to inform Building Energy Models (BEMs) through the development of a pipeline that begins with a drone survey of a building and ends with an accurate representation of anomalies on BEMs ready for simulation. The group has explored the integration of drones with ASHRAE Standard 211P for Commercial Audits and integration of various Nondestructive Testing (NDT) techniques in that process. As well as utilizing aerial photogrammetry techniques coupled with thermal imaging to produce 3D models.

Drone surveying various building envelope properties.

Review of NDT for Building Diagnostic Inspections

This project presents a scoping literature review of select Non-destructive Testing (NDT) techniques for building envelope scanning and surveying for thermodynamic diagnostics. The investigation focuses specifically on reviewing six NDT techniques: Ground Penetrating Radar (GPR), Light Detection and Ranging (LiDAR)/Laser Scanning, Thermography, Ultrasound, Close-Range Photogrammetry and Through Wall Imaging Radar (TWIR). The aim is to identify knowledge gaps in terms of their use in accurately characterizing envelope compositions for further integration in Building Energy Modeling (BEM).

The 3D cloud point was reconstructed with its local coordinate system by using photogrammetry techniques to process UAV-images captured in a spiral flight path. The location (3D coordinates in the local coordinate system) of the RGB and IR images for close-range façade inspection were identified by the proposed image matching and transformation algorithms.

Imagery Façade Anomalies Localization and Visualization

Aiming at locating the detected façade anomalies in IR and RGB images to a 3D building model, this project uses computer vision techniques to identify the 3D coordinates of UAV-captured close-range façade inspection images within the reconstructed 3D reference cloud points. 


Kaiwen Chen's headshot

Kaiwen Chen, Ph.D.

Post-Doctoral Scholar
Yasser El Masri's headshot

Yasser El Masri

Ph.D. Student
Eleanna Panagoulia's headshot

Eleanna Panagoulia

Ph.D. Student
Tarek Rakha's headshot

Tarek Rakha

Ph.D., Assistant Professor


If you can't find the information you were looking for, we'll get you to the right place.
Contact Us