中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Damage area identification of underwater structures based on wavelength difference of light source

文献类型:期刊论文

作者Wang, Xiang4,6; Xu, Hanhua3,5; Wang, Jinchao2,6; Wang, Baoliang1
刊名JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
出版日期2022-03-09
页码15
关键词Underwater structures Damage area Automatic identification Image processing Structure characterization
ISSN号2190-5452
DOI10.1007/s13349-022-00558-4
英文摘要Traditional optical detection of underwater structures suffers from imaging blur affecting underwater object detection tasks. Hence, this work proposes a damaged area recognition method for underwater structures that exploits the differential characteristics of various light source wavelengths, solving the automatic recognition problem of fuzzy images representing underwater structures. Specifically, this paper constructs the spectral variance, local, and global feature representations of an optical image and presents an underwater structure by exploiting the various characteristics of the component images corresponding to different wavelengths. Multiple image features are organically fused through multivariate data fusion, enhancing the optical image of underwater structures. At the same time, we also developed a quantitative characterization method appropriate for underwater structure damage region estimation in optical images that effectively realizes the feature quantization process of the damaged region. Finally, we demonstrate the feasibility and effectiveness of the proposed method on an actual engineering test project. The results highlight that our method improves the image quality and recognition ability of the damaged areas, affording their automatic recognition. Considering image quantization, the suggested technique effectively realizes the quantitative characterization of a damaged area and provides the data support for the health diagnosis of underwater structures.
资助项目Open Projects Foundation of State Key Laboratory for Health and Safety of Bridge Structures[BHSKL-20-05-GF] ; National Natural Science Foundation for the Youth of China[41902294] ; Key Research and Development Plan of Zhejiang Province[2021C03185]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000766494400001
出版者SPRINGER HEIDELBERG
源URL[http://119.78.100.198/handle/2S6PX9GI/34663]  
专题中科院武汉岩土力学所
通讯作者Wang, Jinchao
作者单位1.Southwest Geotech & Design Inst China Nucl Ind, Chengdu 610052, Peoples R China
2.Chinese Acad Sci, Inst Rock & Soil Mech, State Key Lab Geomech & Geotech Engn, Wuhan 430071, Peoples R China
3.Yunnan Key Lab Geotech Engn & Geohazards, Kunming 650051, Yunnan, Peoples R China
4.China Railway Bridge Sci Res Inst Ltd, Wuhan 430034, Peoples R China
5.Kunming Prospecting Design Inst China Nonferrous, Kunming 650051, Yunnan, Peoples R China
6.State Key Lab Hlth & Safety Bridge Struct, Wuhan 430034, Peoples R China
推荐引用方式
GB/T 7714
Wang, Xiang,Xu, Hanhua,Wang, Jinchao,et al. Damage area identification of underwater structures based on wavelength difference of light source[J]. JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING,2022:15.
APA Wang, Xiang,Xu, Hanhua,Wang, Jinchao,&Wang, Baoliang.(2022).Damage area identification of underwater structures based on wavelength difference of light source.JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING,15.
MLA Wang, Xiang,et al."Damage area identification of underwater structures based on wavelength difference of light source".JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING (2022):15.

入库方式: OAI收割

来源:武汉岩土力学研究所

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。