TL-Net: A Novel Network for Transmission Line Scenes Classification

• Published in: Energies (Basel) Vol. 13; no. 15; p. 3910
• Main Authors: Li, Hongchen, Yang, Zhong, Han, Jiaming, Lai, Shangxiang, Zhang, Qiuyan, Zhang, Chi, Fang, Qianhui, Hu, Guoxiong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2020
• Subjects: Accuracy; Algorithms; Classification; Data collection; Datasets; Deep learning; deep neural network; Efficiency; Electricity; image classification; Inspections; Machine learning; Methods; Neural networks; Semantics; Sustainability; transmission lines inspection; unmanned aerial vehicle; voting classification strategy
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en13153910

With the development of unmanned aerial vehicle (UAV) control technology, one of the recent trends in this research domain is to utilize UAVs to perform non-contact transmission line inspection. The RGB camera mounted on UAVs collects large numbers of images during the transmission line inspection, but most of them contain no critical components of transmission lines. Hence, it is a momentous task to adopt image classification algorithms to distinguish key images from all aerial images. In this work, we propose a novel classification method to remove redundant data and retain informative images. A novel transmission line scene dataset, namely TLS_dataset, is built to evaluate the classification performance of networks. Then, we propose a novel convolutional neural network (CNN), namely TL-Net, to classify transmission line scenes. In comparison to other typical deep learning networks, TL-Nets gain better classification accuracy and less memory consumption. The experimental results show that TL-Net101 gains 99.68% test accuracy on the TLS_dataset.