Real-time segmentation of various insulators using generative adversarial networks

doi:10.1049/iet-cvi.2017.0591

	Real-time segmentation of various insulators using generative adversarial networks
	Chang, Wenkai1,2 ; Yang, Guodong1 ; Yu, Junzhi1 ; Liang, Zize1
刊名	IET COMPUTER VISION
	2018-08-01
卷号	12 期号:5 页码:596-602
关键词	image segmentation insulators neural nets power engineering computing real-time pixel-level segmentation generative adversarial networks insulator segmentation algorithm cluttered background artificial thresholds compact end-to-end neural network visual saliency map proposed two-stage training segmentation quality
ISSN号	1751-9632
DOI	10.1049/iet-cvi.2017.0591
通讯作者	Chang, Wenkai(changwenkai2013@ia.ac.cn)
英文摘要	The conventional inspection of fragile insulators is critical to grid operation and insulator segmentation is the basis of inspection. However, the segmentation of various insulators is still difficult because of the great differences in colour and shape, as well as the cluttered background. Traditional insulator segmentation algorithms need many artificial thresholds, thereby limiting the adaptability of algorithms. A compact end-to-end neural network, which is trained in the framework of conditional generative adversarial networks, is proposed for the real-time pixel-level segmentation of insulators. The input image is mapped to a visual saliency map, and various insulators with different poses are filtered out at the same time. The proposed two-stage training and empty samples are also used to improve the segmentation quality. Extensive experiments and comparisons are performed on many real-world images. The experimental results demonstrate superior segmentation and real-time performance. Meanwhile, the effectiveness of the proposed training strategies and the trade-off between performance and speed are analysed in detail.
资助项目	National Natural Science Foundation of China[61403374] ; National Natural Science Foundation of China[61725305] ; State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources[LAPS16006]
WOS关键词	ACTIVE CONTOUR MODEL ; LINE INSULATORS ; AERIAL IMAGES ; SVM
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	INST ENGINEERING TECHNOLOGY-IET
WOS记录号	WOS:000439520600005
资助机构	National Natural Science Foundation of China ; State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/26327]
专题	中国科学院自动化研究所
通讯作者	Chang, Wenkai
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Chang, Wenkai,Yang, Guodong,Yu, Junzhi,et al. Real-time segmentation of various insulators using generative adversarial networks[J]. IET COMPUTER VISION,2018,12(5):596-602.
APA	Chang, Wenkai,Yang, Guodong,Yu, Junzhi,&Liang, Zize.(2018).Real-time segmentation of various insulators using generative adversarial networks.IET COMPUTER VISION,12(5),596-602.
MLA	Chang, Wenkai,et al."Real-time segmentation of various insulators using generative adversarial networks".IET COMPUTER VISION 12.5(2018):596-602.