How can overhead imagery and 3D sensing improve roadway safety assessment and traffic understanding? Transportation research applies computer vision and machine learning to crash risk, traffic dynamics, and infrastructure monitoring. Recent work includes beta distribution learning for reliable roadway crash risk assessment, multi-scale satellite imagery for fatal crash risk estimation, fully automated roadway safety assessment using LiDAR and overhead imagery (FARSA), and remote estimation of free-flow speeds. These projects sit within our broader geospatial AI portfolio, targeting public-safety outcomes from aerial and LiDAR data.
Spotlight publications tagged for this research area.