Affiliation:
1. School of Electrical and Automation, Wuhan University, Wuhan 430072, China
2. Hubei Key Laboratory of Power Equipment & System Security for Integrated Energy, Wuhan 430072, China
Abstract
The accurate and efficient detection of power lines and towers in aerial drone images with complex backgrounds is crucial for the safety of power grid operations and low-altitude drone flights. In this paper, we propose a new method that enhances the deep learning segmentation model UNet algorithm called TLSUNet. We enhance the UNet algorithm by using a lightweight backbone structure to extract the features and then reconstructing them with contextual information features. In this network model, to reduce its parameters and computational complexity, we adopt DFC-GhostNet (Dubbed Full Connected) as the backbone feature extraction network, which is composed of the DFC-GhostBottleneck structure and uses asymmetric convolution to capture long-distance targets in transmission lines, thus enhancing the model’s extraction capability. Additionally, we design a hybrid feature extraction module based on convolution and a transformer to refine deep semantic features and improve the model’s ability to locate towers and transmission lines in complex environments. Finally, we adopt the up-sampling operator CARAFE (Content-Aware Re-Assembly of FEature) to improve segmentation accuracy by enhancing target restoration using contextual neighborhood pixel information correlation under feature decoding. Our experiments on public aerial photography datasets demonstrate that the improved model requires only 8.3% of the original model’s computational effort and has only 21.4% of the original model’s parameters, while achieving a reduction in inference speed delay by 0.012 s. The segmentation metrics also showed significant improvements, with the mIOU improving from 79.75% to 86.46% and the mDice improving from 87.83% to 92.40%. These results confirm the effectiveness of our proposed method.
Funder
National Key R & D Program of China
Subject
Artificial Intelligence,Computer Science Applications,Aerospace Engineering,Information Systems,Control and Systems Engineering
Reference41 articles.
1. Image classification and feature extraction of transmission line based on color space variable;Zhou;Power Syst. Prot. Control,2018
2. A threshold selection method from gray-level histograms;Otsu;IEEE Trans. Syst. Man Cybern.,1979
3. Automatic Extraction Algorithm of Power Line in Complex Background;Zhao;High Volt. Eng.,2019
4. A statistical and geometrical edge detector for SAR images;Touzi;IEEE Trans. Geosci. Remote Sens.,1988
5. Power Line Extraction Algorithm Based on Local Context Information;Zhao;High Volt. Eng.,2021
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献