6 papers
Looks Can be Deceiving: Annotator and Reviewer Performance Across Imagery Sources in Crowd-Sourced Aerial Damage Assessment
Thomas Manzini, Priyankari Perali, Raisa Karnik +2
This paper presents the first known empirical investigation of annotator and reviewer performance across multi-source remotely sensed imagery, evaluating human labeling across dron…
A Benchmark Dataset for Spatially Aligned Road Damage Assessment in Small Uncrewed Aerial Systems Disaster Imagery
Thomas Manzini, Priyankari Perali, Raisa Karnik +1
This paper presents the largest known benchmark dataset for road damage assessment and road alignment, and provides 18 baseline models trained on the CRASAR-U-DRIODs dataset's post…
Deploying Rapid Damage Assessments from sUAS Imagery for Disaster Response
Thomas Manzini, Priyankari Perali, Robin R. Murphy
This paper presents the first AI/ML system for automating building damage assessment in uncrewed aerial systems (sUAS) imagery to be deployed operationally during federally declare…
Challenges and Research Directions from the Operational Use of a Machine Learning Damage Assessment System via Small Uncrewed Aerial Systems at Hurricanes Debby and Helene
Thomas Manzini, Priyankari Perali, Robin R. Murphy +1
This paper details four principal challenges encountered with machine learning (ML) damage assessment using small uncrewed aerial systems (sUAS) at Hurricanes Debby and Helene that…
Non-Uniform Spatial Alignment Errors in sUAS Imagery From Wide-Area Disasters
Thomas Manzini, Priyankari Perali, Raisa Karnik +3
This work presents the first quantitative study of alignment errors between small uncrewed aerial systems (sUAS) georectified imagery and a priori building polygons and finds that…
Now you see it, Now you don't: Damage Label Agreement in Drone & Satellite Post-Disaster Imagery
Thomas Manzini, Priyankari Perali, Jayesh Tripathi +1
This paper audits damage labels derived from coincident satellite and drone aerial imagery for 15,814 buildings across Hurricanes Ian, Michael, and Harvey, finding 29.02% label dis…