Department of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China.
State Grid Information & Telecommunication Group Co., Ltd., Beijing 102211, China.
Sensors (Basel). 2022 Aug 18;22(16):6186. doi: 10.3390/s22166186.
Aerial insulator defect images have some features. For instance, the complex background and small target of defects would make it difficult to detect insulator defects quickly and accurately. To solve the problem of low accuracy of insulator defect detection, this paper concerns the shortcomings of IoU and the sensitivity of small targets to the model regression accuracy. An improved SIoU loss function was proposed based on the regular influence of regression direction on the accuracy. This loss function can accelerate the convergence of the model and make it achieve better results in regressions. For complex backgrounds, ECA (Efficient Channel Attention Module) is embedded between the backbone and the feature fusion layer of the model to reduce the influence of redundant features on the detection accuracy and make progress in the aspect. As a result, these experiments show that the improved model achieved 97.18% mAP which is 2.74% higher than before, and the detection speed could reach 71 fps. To some extent, it can detect insulator and its defects accurately and in real-time.
绝缘子缺陷图像具有一些特点。例如，缺陷的复杂背景和小目标使得快速准确地检测绝缘子缺陷变得困难。为了解决绝缘子缺陷检测精度低的问题，本文针对 IoU 的缺点以及小目标对模型回归精度的敏感性，提出了一种基于回归方向对精度正则影响的改进 SIoU 损失函数。该损失函数可以加速模型的收敛，使其在回归方面取得更好的结果。对于复杂的背景，在模型的骨干和特征融合层之间嵌入了 ECA（高效通道注意力模块），以减少冗余特征对检测精度的影响，并在这方面取得进展。因此，这些实验表明，改进后的模型实现了 97.18%的 mAP，比之前提高了 2.74%，检测速度可以达到 71fps。在一定程度上，可以实现对绝缘子及其缺陷的准确实时检测。
