Wind Turbine Surface Damage Detection by Deep Learning Aided Drone Inspection Analysis

将深度学习应用于风力机叶片的无人机图像，以检测前缘侵蚀、涡流发生器面板（包括缺齿）和雷电接闪器。文章比较了采用多种骨干网络的 Faster R-CNN，多尺度金字塔增强配合分块显著提高了精度。模型在丹麦的风力机图像上训练，并公开了一台风力机的图像集。向人工分析员展示模型建议缩短了他们处理每张图像的时间。

主要发现

• Best mAP 81.1% (Inception-ResNet-V2 with pyramid, patching and regular augmentation) versus 27.5% with no augmentation
• Inference 1.36-2.11 s per high-resolution image versus about 200 s for a human, or about 131 s with model suggestions
• Human precision 83.2%; humans aided by suggestions 85.3%
• Public DTU dataset of 701 images of one turbine released

局限

• Surface damage only; internal damage such as delamination out of scope
• Small, imbalanced training data (e.g. 17 lightning-receptor annotations); lightning receptors 71.6% vs 98.7% for humans
• Main dataset private; public set covers a single turbine
• IoU threshold reported inconsistently in the paper