Novel Feature Fusion Module-Based Detector for Small Insulator Defect Detection
Gao, Zishu1,2; Yang, Guodong1,2; Li, En1,2; Liang, Zize1,2
发表期刊IEEE SENSORS JOURNAL
ISSN1530-437X
2021-08-01
卷号21期号:15页码:16807-16814
通讯作者Yang, Guodong(guodong.yang@ia.ac.cn)
摘要The failure of an insulator may compromise the safety of the entire power transmission system. Therefore, insulator defect detection is vital for the safe operation of power systems. However, insulator defects in an insulator image may have varying sizes, and several currently available methods do not have satisfactory detection accuracy for small defects. To address this issue, we propose an improved detection network for small insulator defects with a batch normalization convolutional block attention module (BN-CBAM) and a feature fusion module. The BN-CBAM is designed to better exploit channel information and enhance the effect of different channels on the feature map. In addition, we propose a feature fusion module that fuses multi-scale features from different layers to improve small object detection performance. Moreover, to address the scarcity of aerial images, a data augmentation method based on the fusion of the target segment and background is introduced. Experiments demonstrate that the proposed method achieves better small insulator defect detection performance than other state-of-the-art approaches. In addition, data augmentation methods enrich sample diversity and enhance the generalizability of the network.
关键词Feature extraction Insulators Sensors Image segmentation Inspection Fuses Support vector machines Insulator defect detection anchor-free object detection data augmentation aerial image
DOI10.1109/JSEN.2021.3073422
收录类别SCI
语种英语
资助项目National Key Research and Development Program of China[2018YFB1307400] ; National Natural Science Foundation[U1713224] ; National Natural Science Foundation[61973300]
项目资助者National Key Research and Development Program of China ; National Natural Science Foundation
WOS研究方向Engineering ; Instruments & Instrumentation ; Physics
WOS类目Engineering, Electrical & Electronic ; Instruments & Instrumentation ; Physics, Applied
WOS记录号WOS:000679541000045
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类多模态智能
引用统计
被引频次:32[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/45555
专题复杂系统管理与控制国家重点实验室_先进机器人
通讯作者Yang, Guodong
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, Sch Artificial Intelligence, Beijing 100049, Peoples R China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Gao, Zishu,Yang, Guodong,Li, En,et al. Novel Feature Fusion Module-Based Detector for Small Insulator Defect Detection[J]. IEEE SENSORS JOURNAL,2021,21(15):16807-16814.
APA Gao, Zishu,Yang, Guodong,Li, En,&Liang, Zize.(2021).Novel Feature Fusion Module-Based Detector for Small Insulator Defect Detection.IEEE SENSORS JOURNAL,21(15),16807-16814.
MLA Gao, Zishu,et al."Novel Feature Fusion Module-Based Detector for Small Insulator Defect Detection".IEEE SENSORS JOURNAL 21.15(2021):16807-16814.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Gao, Zishu]的文章
[Yang, Guodong]的文章
[Li, En]的文章
百度学术
百度学术中相似的文章
[Gao, Zishu]的文章
[Yang, Guodong]的文章
[Li, En]的文章
必应学术
必应学术中相似的文章
[Gao, Zishu]的文章
[Yang, Guodong]的文章
[Li, En]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。