Summary of research interests
- Computer Vision
- Building Information Modeling and Digital Twins
- Technology Adoption
- Information Systems
Current – ASU
The mission of Edifice Lab is to automate the creation of immersive digital learning experiences for the builders and stewards of infrastructure. We accomplish this by developing computer vision technologies for digitizing and abstracting the built environment. Go to edificelab.com for the latest.
Computer vision is the subfield of artificial intelligence that trains computers to interpret visual data. In the context of the built environment, it is used to automatically monitor safety and security, evaluate efficiency, track progress, detect defects, guide robotic systems, and support remote presence of scarce expert resources. At the Edifice Lab, we explore the sensors used to collect visual data, the tools used to fuse data into unified digital representations, and the algorithms available to automatically analyze these representations to extract useful insights for improving facility construction and operations.
Past – UTexas
During my PhD, I worked on a collaborative project called:
Living Building Information Model (BIM): A Layered Approach for Automatic and Continuous Built Environment Model Update
You can read the abstract on the National Science Foundation website.
The project aims to improve the information practices of people who operate, maintain, and renovate facilities.
Specifically, by applying tools found in machine learning and computer vision, we made Building Information Models easier to update throughout the life-cycle of a facility.
We are in the process of releasing an RGB-D dataset of building facilities for semantic segmentation research – 3DFacilities.
Past – UWaterloo
Team from the University of Waterloo
My master’s degree was focused on developing automated quality control tools for industrial construction, specifically pipe spool fabrication.
By analyzing point clouds captured by laser scanners, we could identify geometrical fabrication errors and mitigate the risk of on-site rework.