Aerial image detection of transmission towers and power lines in transmission lines is the key technology for unmanned aerial vehicles (UAVs) intelligent inspection, path planning, and obstacle avoidance. Different from previous transmission line detection methods, this work uses an instance segmentation algorithm to detect transmission towers and power lines. However, the aerial survey image’s large size and high-resolution result in a low signal-to-noise ratio, while the high length-to-diameter ratio of power lines presents great challenges. To solve these issues, this article conducts instance segmentation of aerial survey images based on the improved Solov2 network. Specifically, the neck of the model has been replaced by path aggregation feature pyramid network (PaFPN) to enhance the feature fusion ability and reduce feature loss. The designed MaskIou branch processes feature relationships before and after the Mask branch of Solov2 and calculates the segmentation loss of each type of mask. Transfer Learning is adopted to pretrain the network and learn data from a single type of lightning conductor so that the network can better identify linear features with high length to diameter ratio that is difficult to recognize. Comparison tests with multiple instance segmentation networks show that the proposed improved network can achieve higher precision in the segmentation.

中文翻译：

---

基于改进Solov2的输电铁塔及电力线路检测

输电线路中输电铁塔和电力线路的航拍图像检测是无人机智能巡检、路径规划和避障的关键技术。与以往的输电线路检测方法不同，本工作使用实例分割算法来检测输电塔和电力线。然而，航测图像的大尺寸和高分辨率导致信噪比较低，而电力线的高长径比也带来了巨大的挑战。为了解决这些问题，本文基于改进的Solov2网络对航测图像进行实例分割。具体来说，模型的颈部被路径聚合特征金字塔网络（PaFPN）取代，以增强特征融合能力并减少特征损失。设计的MaskIou分支处理Solov2的Mask分支前后的特征关系，并计算每种类型mask的分割损失。采用迁移学习对网络进行预训练，学习单一类型避雷导体的数据，使网络能够更好地识别难以识别的高长径比的线状特征。与多个实例分割网络的对比测试表明，所提出的改进网络可以实现更高的分割精度。