AI 中文总结
该研究提出两阶段视觉系统，用单类YOLO检测器定位脑电图帽电极，经几何阶段验证位置。通过留一法交叉验证评估，介绍了不同帽尺寸及增强方法对检测的影响，还提及骨干网络保持实时吞吐量，能实时检测并验证电极位置。
AI 中文摘要
我们提出了一个两阶段视觉系统，可在实时网络摄像头流中检测脑电图帽电极，并实时验证其解剖位置。单类YOLO检测器定位电极，几何阶段根据面部标志将每个检测结果分配到一个指定的10-20角色。在对五名佩戴经临床验证的小/中/大尺寸帽的受试者进行受试者不相交的留一法交叉验证时，检测器在五个留出的折叠中mAP@.5 = 0.94 +/- 0.07（汇总为0.96）。专门的留一顶法轴，无论受试者如何，留出帽的每一帧，中号和大号的mAP@.5在留一法的0.01范围内（0.97，0.97），而小号降至0.72 +/- 0.28，这种差距与受试者熟悉度而非帽的样式有关。几何增强（旋转、透视、混合）在不增加推理成本的情况下提高了平面滚动鲁棒性和时间电极召回率，地标驱动的头部裁剪扩展了可用距离范围，在0.6倍表观比例下将mAP@.5从0.23提高到0.45。紧凑的移动候选骨干（YOLOv10n）使检测器在640像素的商品CPU上保持实时吞吐量（19 FPS）。
英文摘要
We present a two-stage vision system that detects EEG cap electrodes in a live webcam stream and validates their anatomical placement in real time. A single-class YOLO detector localises electrodes; a geometric stage assigns each detection to a named 10-20 role from facial landmarks. Evaluating under subject-disjoint leave-one-subject-out (LOSO) cross-validation across five subjects wearing the clinically-validated Small/Medium/Large caps, the detector attains mAP@.5 = 0.94 +/- 0.07 across five held-out folds (0.96 pooled). A dedicated leave-one-cap-out axis, holding out every frame of a cap regardless of subject, leaves Medium and Large mAP@.5 within 0.01 of LOSO (0.97, 0.97) while Small drops to 0.72 +/- 0.28, a gap confounded with subject familiarity rather than cap style. Geometric augmentation (rotation, perspective, mixup) improves in-plane-roll robustness and temporal-electrode recall at no inference cost, and a landmark-driven head crop extends the usable distance range, lifting mAP@.5 from 0.23 to 0.45 at 0.6 x apparent scale. A compact mobile-candidate backbone (YOLOv10n) keeps the detector at real-time throughput (19 FPS) on a commodity CPU at 640 px.
CommentsPreprint. 13 pages, 7 figures, 4 tables
