arXiv cs.CV· Osman Ali (Manufacturing Metrology Team, University of Nottingham, Nottingham, United Kingdom), Xiangjun Kong (Manufacturing Metrology Team, University of Nottingham, Nottingham, United Kingdom), Tibebe Yalew (Manufacturing Metrology Team, University of Nottingham, Nottingham, United Kingdom), Waiel Elmadih (Taraz Metrology Ltd., Nottingham, United Kingdom), Samanta Piano (Manufacturing Metrology Team, University of Nottingham, Nottingham, United Kingdom)·· 5 小时前AI 评分17
RACE-FPP：面向条纹投影轮廓术的鲁棒 AI 辅助标定增强方法
RACE-FPP: A Robust AI-assisted Characterisation Enhancement for Fringe Projection Profilometry
AI 导读
诺丁汉大学团队提出 RACE-FPP，将深度学习角点检测融入条纹投影轮廓术（FPP）标准标定流程，并显式分析定位误差在整条标定链中的传播。在干净与退化图像混合数据集上，相机重投影误差从 1.237 像素降至 0.259 像素，投影仪重投影误差降低约 50%，重建工件的几何精度也优于传统流程。
来源：arXiv cs.CV · arxiv.org