The Potential of Hyperspectral Image Classification for Oil Spill Mapping

被引：40
作者：
Kang, Xudong [1 ]
Wang, Zihao [2 ,3 ]
Duan, Puhong [2 ,3 ]
Wei, Xiaohui [2 ,3 ]
机构：
[1] Hunan Univ, Sch Robot, Changsha 410082, Hunan, Peoples R China
[2] Hunan Univ, Coll Elect & Informat Engn, Changsha 410082, Hunan, Peoples R China
[3] Hunan Univ, Key Lab Visual Percept & Artificial Intelligence, Changsha 410082, Hunan, Peoples R China
来源：
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2022年 / 60卷
基金：
美国国家科学基金会; 中国博士后科学基金; 中国国家自然科学基金;
关键词：
Oils; Feature extraction; Hyperspectral imaging; Accidents; Principal component analysis; Visualization; Support vector machines; Deep learning; hyperspectral images (HSIs); image classification; machine learning; oil spill; FEATURE-EXTRACTION; SPARSE REPRESENTATION; POLLUTION; INFORMATION; SATELLITE; LESSONS; FUSION; AREAS; BAY;
D O I：
10.1109/TGRS.2022.3205966
中图分类号：
P3 [地球物理学]; P59 [地球化学];
学科分类号：
0708 ; 070902 ;
摘要：
Oil spill mapping is a very challenging problem in marine environmental monitoring. In this article, the potential of hyperspectral image (HSI) classification for mapping oil spills is comprehensively investigated. First, several representative HSI classification methods are reviewed in a general framework. Second, three oil spill mapping cases are designed to analyze the performance of different classification methods in detecting spatial distribution, classifying the type, and estimating the thickness of oil spills. Finally, the experimental results are analyzed in detail, and some conclusions are given, which brings a comprehensive understanding to scholars who are interested in the fields of hyperspectral remote sensing and oil spill mapping.
引用
收藏
页数：15
相关论文
共 94 条
[81]   An overview of statistical learning theory [J].
Vapnik, VN .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05) :988-999
[82]  
Vaswani A, 2017, ADV NEUR IN, V30
[83]   Hyperspectral Image Classification With Independent Component Discriminant Analysis [J].
Villa, Alberto ;
Benediktsson, Jon Atli ;
Chanussot, Jocelyn ;
Jutten, Christian .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (12) :4865-4876
[84]   Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis [J].
Wang, Jing ;
Chang, Chein-I .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (06) :1586-1600
[85]   A damage assessment model of oil spill accident combining historical data and satellite remote sensing information: A case study in Penglai 19-3 oil spill accident of China [J].
Wei, Lai ;
Hu, Zhuowei ;
Dong, Lin ;
Zhao, Wenji .
MARINE POLLUTION BULLETIN, 2015, 91 (01) :258-271
[86]   Hyperspectral Remote Sensing Image Classification Based on Rotation Forest [J].
Xia, Junshi ;
Du, Peijun ;
He, Xiyan ;
Chanussot, Jocelyn .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2014, 11 (01) :239-243
[87]   Towards interpreting multi-temporal deep learning models in crop mapping [J].
Xu, Jinfan ;
Yang, Jie ;
Xiong, Xingguo ;
Li, Haifeng ;
Huang, Jingfeng ;
Ting, K. C. ;
Ying, Yibin ;
Lin, Tao .
REMOTE SENSING OF ENVIRONMENT, 2021, 264
[88]   Structure Extraction from Texture via Relative Total Variation [J].
Xu, Li ;
Yan, Qiong ;
Xia, Yang ;
Jia, Jiaya .
ACM TRANSACTIONS ON GRAPHICS, 2012, 31 (06)
[89]   Nonlocal Patch Tensor Sparse Representation for Hyperspectral Image Super-Resolution [J].
Xu, Yang ;
Wu, Zebin ;
Chanussot, Jocelyn ;
Wei, Zhihui .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (06) :3034-3047
[90]   Image Super-Resolution Via Sparse Representation [J].
Yang, Jianchao ;
Wright, John ;
Huang, Thomas S. ;
Ma, Yi .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2010, 19 (11) :2861-2873
12345678910