用合成数据训练无人机巡检风力发电机的特征检测模型
Wind Turbine Feature Detection Using Deep Learning and Synthetic Data
- 用可控参数生成合成图像，扩充训练数据多样性
- 仅在合成数据上训练的YOLOv11模型在真实图像上达到0.97的定位精度
- 适合需要高鲁棒性视觉检测的工业巡检场景
针对风力发电机叶片自主无人机巡检，准确识别风力发电机及其关键特征对安全定位和避障至关重要。现有深度学习方法多依赖人工标注的真实图像，受限于天气、光照、机型和图像复杂度等因素，训练数据数量与多样性不足。本文提出一种合成训练数据生成方法，可控制视觉与环境因素变化，提升数据多样性并构造更具挑战性的学习场景。进一步，我们仅使用合成风力发电机图像，结合改进的损失函数训练了YOLOv11特征检测网络，实现图像中风力发电机及其关键特征的检测。该模型在合成图像和一组真实世界风力发电机图像上均进行了评估，表现出色，在未参与训练的真实图像上实现了0.97的Pose mAP50-95性能。
原文摘要 · Abstract (English)
For the autonomous drone-based inspection of wind turbine (WT) blades, accurate detection of the WT and its key features is essential for safe drone positioning and collision avoidance. Existing deep learning methods typically rely on manually labeled real-world images, which limits both the quantity and the diversity of training datasets in terms of weather conditions, lighting, turbine types, and image complexity. In this paper, we propose a method to generate synthetic training data that allows controlled variation of visual and environmental factors, increasing the diversity and hence creating challenging learning scenarios. Furthermore, we train a YOLOv11 feature detection network solely on synthetic WT images with a modified loss function, to detect WTs and their key features within an image. The resulting network is evaluated both using synthetic images and a set of real-world WT images and shows promising performance across both synthetic and real-world data, achieving a Pose mAP50-95 of 0.97 on real images never seen during training.
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。