Insulator Segmentation for Power Line Inspection Based on Modified Conditional Generative Adversarial Network
Joint Authors
Gao, Zishu
Yang, Guodong
Li, En
Shen, Tianyu
Wang, Zhe
Tian, Yunong
Wang, Hao
Liang, Zize
Source
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-8, 8 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-11-12
Country of Publication
Egypt
No. of Pages
8
Main Subjects
Abstract EN
There are a large number of insulators on the transmission line, and insulator damage will have a major impact on power supply security.
Image-based segmentation of the insulators in the power transmission lines is a premise and also a critical task for power line inspection.
In this paper, a modified conditional generative adversarial network for insulator pixel-level segmentation is proposed.
The generator is reconstructed by encoder-decoder layers with asymmetric convolution kernel which can simplify the network complexity and extract more kinds of feature information.
The discriminator is composed of a fully convolutional network based on patchGAN and learns the loss to train the generator.
It is verified in experiments that the proposed method has better performances on mIoU and computational efficiency than Pix2pix, SegNet, and other state-of-the-art networks.
American Psychological Association (APA)
Gao, Zishu& Yang, Guodong& Li, En& Shen, Tianyu& Wang, Zhe& Tian, Yunong…[et al.]. 2019. Insulator Segmentation for Power Line Inspection Based on Modified Conditional Generative Adversarial Network. Journal of Sensors،Vol. 2019, no. 2019, pp.1-8.
https://search.emarefa.net/detail/BIM-1187636
Modern Language Association (MLA)
Gao, Zishu…[et al.]. Insulator Segmentation for Power Line Inspection Based on Modified Conditional Generative Adversarial Network. Journal of Sensors No. 2019 (2019), pp.1-8.
https://search.emarefa.net/detail/BIM-1187636
American Medical Association (AMA)
Gao, Zishu& Yang, Guodong& Li, En& Shen, Tianyu& Wang, Zhe& Tian, Yunong…[et al.]. Insulator Segmentation for Power Line Inspection Based on Modified Conditional Generative Adversarial Network. Journal of Sensors. 2019. Vol. 2019, no. 2019, pp.1-8.
https://search.emarefa.net/detail/BIM-1187636
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1187636