P.Eng. / Fuel Research Scientist / Computer Vision
Reeghan Osmond
Computer vision and 3D imaging engineer working on X-ray computed tomography, industrial inspection, and applied machine learning for materials research, with work spanning imaging hardware, 3D geometry, metrology, model development, and reporting.
At Canadian Nuclear Laboratories, my work sits between imaging hardware, model development, 3D geometry, metrology, and reporting. I build automated XCT analysis workflows for segmentation, instance detection, orientation estimation, and QA reporting, help oversee a lab handling more than 130 analyses per year, and have led research proposals totaling more than $1.5M in combined funding.
Selected projects
Technical projects from research, industrial inspection, and open-source work.
Automated 3D XCT analysis for advanced fuel
Python pipelines for volumetric segmentation, instance detection, orientation estimation, metrology, mesh export, and QA reporting for nuclear fuel research.
NuclearFlowAI
In-progress nuclear document workflow demo with cited retrieval, saved findings, summary export, audit logging, and public usage caps.
Robotic bin-picking perception pipeline
YOLO visible instance segmentation, depth back-projection, object-level geometry features, and a PyTorch ranking model for cluttered industrial scenes.
BEV road corridor segmentation
Argoverse 2 camera, LiDAR, ego pose, and HD map geometry converted into BEV inputs for main road corridor segmentation baselines.
Publications and talks
-
Uncovering the inner workings of poppy seed-sized nuclear fuel
Public CNL story on XCT, TRISO fuel research, and non-destructive imaging.
-
Inferring the Internal Geometry and Performance of Coated Particle Fuel
Journal of Nuclear Materials, 2026.
-
Fuel Performance Simulations of TRISO Particle Geometries Derived from XCT
Journal of Nuclear Materials, 2025.
-
AI in Nuclear Science
Panel presentation, October 2025.