Advanced detection and segmentation of parabolic trough collector and Fresnel mirrors for CSP maintenance using YOLOv8 and segment anything model
Mohamed Boujoudar, Amine Moulay Taj, Yasser El Jarida, Ibtissam Bouarfa, Ammar Mouaky, Massaab El Ydrissi, El Ghali Bennouna, Hicham Ghennioui · The Visual Computer (Springer) · 2026
DOI ·
A two-stage machine learning framework for automated mirror detection and segmentation in concentrated solar power (CSP) systems, focusing on parabolic trough collector (PTC) and Fresnel systems. Leverages YOLOv8 for bounding box generation and the Segment Anything Model (SAM) for detailed segmentation. Evaluated on a diverse dataset of 4000 images captured at the Green Energy Park facility under various conditions.