ISSD：基于无人机系统的绝缘子和间隔棒在线检测改进型SSD

ISSD: Improved SSD for Insulator and Spacer Online Detection Based on UAV System.

作者信息

Liu Xuan, Li Yong, Shuang Feng, Gao Fang, Zhou Xiang, Chen Xingzhi

机构信息

College of Electrical Engineering, Guangxi University, Nanning 530000, China.

出版信息

Sensors (Basel). 2020 Dec 5;20(23):6961. doi: 10.3390/s20236961.

DOI:10.3390/s20236961

PMID:33291473

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7729514/

Abstract

In power inspection tasks, the insulator and spacer are important inspection objects. UAV (unmanned aerial vehicle) power inspection is becoming more and more popular. However, due to the limited computing resources carried by a UAV, a lighter model with small model size, high detection accuracy, and fast detection speed is needed to achieve online detection. In order to realize the online detection of power inspection objects, we propose an improved SSD (single shot multibox detector) insulator and spacer detection algorithm using the power inspection images collected by a UAV. In the proposed algorithm, the lightweight network MnasNet is used as the feature extraction network to generate feature maps. Then, two multiscale feature fusion methods are used to fuse multiple feature maps. Lastly, a power inspection object dataset containing insulators and spacers based on aerial images is built, and the performance of the proposed algorithm is tested on real aerial images and videos. Experimental results show that the proposed algorithm can efficiently detect insulators and spacers. Compared with existing algorithms, the proposed algorithm has the advantages of small model size and fast detection speed. The detection accuracy can achieve 93.8%. The detection time of a single image on TX2 (NVIDIA Jetson TX2) is 154 ms and the capture rate on TX2 is 8.27 fps, which allows realizing online detection.

摘要

在电力巡检任务中，绝缘子和间隔棒是重要的巡检对象。无人机电力巡检正变得越来越流行。然而，由于无人机携带的计算资源有限，需要一个模型尺寸小、检测精度高、检测速度快的更轻量级模型来实现在线检测。为了实现电力巡检对象的在线检测，我们利用无人机采集的电力巡检图像，提出了一种改进的SSD（单阶段多框检测器）绝缘子和间隔棒检测算法。在所提出的算法中，轻量级网络MnasNet被用作特征提取网络来生成特征图。然后，使用两种多尺度特征融合方法来融合多个特征图。最后，构建了一个基于航空图像的包含绝缘子和间隔棒的电力巡检对象数据集，并在真实航空图像和视频上测试了所提算法的性能。实验结果表明，所提算法能够高效地检测绝缘子和间隔棒。与现有算法相比，所提算法具有模型尺寸小和检测速度快的优点。检测精度可达93.8%。在TX2（英伟达Jetson TX2）上单张图像的检测时间为154毫秒，TX2上的捕获率为8.27帧/秒，这使得能够实现在线检测。