用摄像头实时检测脑电帽电极位置，确保佩戴准确。
Real-Time EEG Cap Electrode Detection for Guided Point-of-Care Placement
- 两阶段视觉系统：先定位电极，再根据脸点匹配解剖位置。
- 在5人数据上平均精度达0.94，小号帽因熟悉度影响降至0.72。
- 适合作业于家庭或急诊场景的脑电检查辅助，无需专业设备。
本文提出一种两阶段视觉系统，可在实时网络摄像头画面中检测脑电帽电极并验证其解剖位置。单类YOLO检测器定位电极；几何阶段结合面部关键点将检测结果映射至10-20标准命名位置。在五名受试者（使用临床验证的小/中/大号帽）的交叉验证中，模型在留一被试（LOSO）条件下平均精度（[email protected]）为0.94±0.07（合并后0.96）。针对不同帽子的留一帽（leave-one-cap-out）测试显示，中、大号帽表现与LOSO接近（0.97, 0.97），小号帽下降至0.72±0.28，该差异由受试者熟悉度导致而非帽型。通过几何增强（旋转、透视、mixup）提升平面内旋转鲁棒性及时间电极召回率，且无推理成本增加；基于关键点的头部裁剪扩展可用距离范围，使0.6倍视图缩放下的精度从0.23提升至0.45。采用轻量级移动端骨干网络（YOLOv10n），在640像素分辨率下实现19帧/秒的实时性能，运行于通用CPU。
原文摘要 · Abstract (English)
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 [email protected] = 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 [email protected] 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 [email protected] 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。