Abstract

A semantic segmentation method based on the fully convolutional network is proposed to detect the buffer layer defect in high voltage cable automatically. One hundred seventy-seven high-resolution X-ray images of cables are collected. FCN-8s and VGG16 backbone are adopted. The results indicated that the FCN-8s achieves the mIoU to 0.67 on the test set, proving to be an efficient way to detect the buffer layer defects.

Details

Title
A Semantic Segmentation Method for Buffer Layer Defect Detection in High Voltage Cable
Author
Zhang, Jun; Duan Xiaoli; Xie, Yi; Duan Jianjia; Huang Fuyong; Zeng Zeyu
Section
NESEE2020-New Energy Science and Environmental Engineering
Publication year
2021
Publication date
2021
Publisher
EDP Sciences
ISSN
25550403
e-ISSN
22671242
Source type
Conference Paper
Language of publication
English
ProQuest document ID
2484275242
Copyright
© 2021. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and conditions, you may use this content in accordance with the terms of the License.