Real-time segmentation of various insulators using generative adversarial networks
文献类型:期刊论文
作者 | Chang, Wenkai1,2; Yang, Guodong1; Yu, Junzhi1; Liang, Zize1 |
刊名 | IET COMPUTER VISION |
出版日期 | 2018-08-01 |
卷号 | 12期号:5页码:596-602 |
ISSN号 | 1751-9632 |
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 |
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. |
WOS关键词 | ACTIVE CONTOUR MODEL ; LINE INSULATORS ; AERIAL IMAGES ; SVM |
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 |
源URL | [http://ir.ia.ac.cn/handle/173211/26327] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室 |
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. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。