One-Class Remote Sensing Classification From Positive and Unlabeled Background Data

doi:10.1109/JSTARS.2020.3025451

	One-Class Remote Sensing Classification From Positive and Unlabeled Background Data
	Li, Wenkai ; Guo, Qinghua1 ; Elkan, Charles 2
	2021
发表期刊	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
ISSN	1939-1404
卷号	14 页码:730-746
摘要	One-class classification is a common situation in remote sensing, where researchers aim to extract a single land type from remotely sensed data. Learning a classifier from labeled positive and unlabeled background data, which is the case-control sampling scenario, is efficient for one-class remote sensing classification because labeled negative data are not necessary for model training. In this study, we propose a novel positive and background learning with constraints (PBLC) algorithm to address this one-class classification problem. With user-specified information of maximum probability as the constraint, PBLC infers the posterior probability of positive class directly in one-step model training. We test PBLC on a synthetic dataset and a real aerial photograph to perform different one-class classification tasks. Experimental results demonstrate that PBLC can successfully train linear and nonlinear classifiers including generalized linear model, artificial neural network, and convolutional neural network. Probabilistic and binary predictions by PBLC are more similar to the gold-standard positive-negative method, outperforming the two-step positive and background learning algorithm that post-calibrates a naive classifier based on an estimated constant. Hence, the proposed PBLC algorithm has the potential to solve one-class classification problems in the case-control sampling scenario.
关键词	Training Remote sensing Classification algorithms Mathematical model Support vector machines Data models Prediction algorithms Case-control sampling labeled and unlabeled data one-class classification positive and background learning with constraints (PBLC) remote sensing
学科领域	Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
DOI	10.1109/JSTARS.2020.3025451
收录类别	SCI
语种	英语
WOS关键词	PRESENCE-ONLY DATA ; LOCALITY DESCRIPTIONS ; IMAGE CLASSIFICATION ; SUPPORT ; EXTRACTION ; SVM
WOS研究方向	Science Citation Index Expanded (SCI-EXPANDED) ; Social Science Citation Index (SSCI)
WOS记录号	WOS:000696430600007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
文献子类	Article
出版地	PISCATAWAY
EISSN	2151-1535
资助机构	Guangdong Basic and Applied Basic Research Foundation [2020A1515010764] ; National Natural Science Foundation of China [41401516] ; State Key Laboratory of Vegetation and Environmental Change [LVEC-2019kf05]
作者邮箱	liwenk3@mail.sysu.edu.cn ; guo.qinghua@gmail.com
作品OA属性	gold
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ibcas.ac.cn/handle/2S10CLM1/26497
专题	植被与环境变化国家重点实验室
作者单位	1.Sun Yat Sen Univ, Sch Geog & Planning, Guangdong Prov Key Lab Urbanizat & Geosimulat, Guangzhou 510275, Guangdong, Peoples R China 2.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing 100093, Peoples R China 3.Univ Calif San Diego, Dept Comp Sci & Engn, La Jolla, CA 92093 USA
推荐引用方式 GB/T 7714	Li, Wenkai,Guo, Qinghua,Elkan, Charles. One-Class Remote Sensing Classification From Positive and Unlabeled Background Data[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2021,14:730-746.
APA	Li, Wenkai,Guo, Qinghua,&Elkan, Charles.(2021).One-Class Remote Sensing Classification From Positive and Unlabeled Background Data.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,14,730-746.
MLA	Li, Wenkai,et al."One-Class Remote Sensing Classification From Positive and Unlabeled Background Data".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 14(2021):730-746.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Li-2021-One-Class Re（11598KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文