One-class remote sensing classification: one-class vs. binary classifiers

doi:10.1080/01431161.2017.1416697

CORC > 植物研究所 > 中国科学院植物研究所 > 植被与环境变化国家重点实验室

	One-class remote sensing classification: one-class vs. binary classifiers
	Deng, Xueqing 3; Li, Wenkai ; Liu, Xiaoping ; Guo, Qinghua 2; Newsam, Shawn 3
刊名	INTERNATIONAL JOURNAL OF REMOTE SENSING
	2018
卷号	39 期号:6 页码:1890-1910
ISSN号	0143-1161
DOI	10.1080/01431161.2017.1416697
文献子类	Article
英文摘要	Many applications of remote sensing only require the classification of a single land type. This is known as the one-class classification problem and it can be performed using either binary classifiers, by treating all other classes as the negative class, or one-class classifiers which only consider the class of interest. The key difference between these two approaches is in their training data and the amount of effort needed to produce it. Binary classifiers require an exhaustively labelled training data set while one-class classifiers are trained using samples of just the class of interest. Given ample and complete training data, binary classifiers generally outperform one-class classifiers. However, what is not clear is which approach is more accurate when given the same amount of labelled training data. That is, for a fixed labelling effort, is it better to use a binary or one-class classifier. This is the question we consider in this article. We compare several binary classifiers, including backpropagation neural networks, support vector machines, and maximum likelihood classifiers, with two one-class classifiers, one-class SVM, and presence and background learning (PBL), on the problem of one-class classification in high-resolution remote sensing imagery. We show that, given a fixed labelling budget, PBL consistently outperforms the other methods. This advantage stems from the fact that PBL is a positive-unlabelled method in which large amounts of readily available unlabelled data is incorporated into the training phase, allowing the classifier to model the negative class more effectively.
学科主题	Remote Sensing ; Imaging Science & Photographic Technology
电子版国际标准刊号	1366-5901
出版地	ABINGDON
WOS关键词	SUPERVISED IMAGE CLASSIFICATION ; SUPPORT VECTOR MACHINES ; NEURAL-NETWORKS ; LAND ; PROBABILITY ; SET
语种	英语
出版者	TAYLOR & FRANCIS LTD
WOS记录号	WOS:000423204500017
资助机构	National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [41401516]
内容类型	期刊论文
源URL	[http://ir.ibcas.ac.cn/handle/2S10CLM1/20640]
专题	植被与环境变化国家重点实验室
作者单位	1.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing, Peoples R China 2.Univ Calif Merced, Elect Engn & Comp Sci, Merced, CA USA 3.Sun Yat Sen Univ, Sch Geog & Planning, Guangdong Prov Key Lab Urbanizat & Geosimulat, Guangzhou 510275, Guangdong, Peoples R China
推荐引用方式 GB/T 7714	Deng, Xueqing,Li, Wenkai,Liu, Xiaoping,et al. One-class remote sensing classification: one-class vs. binary classifiers[J]. INTERNATIONAL JOURNAL OF REMOTE SENSING,2018,39(6):1890-1910.
APA	Deng, Xueqing,Li, Wenkai,Liu, Xiaoping,Guo, Qinghua,&Newsam, Shawn.(2018).One-class remote sensing classification: one-class vs. binary classifiers.INTERNATIONAL JOURNAL OF REMOTE SENSING,39(6),1890-1910.
MLA	Deng, Xueqing,et al."One-class remote sensing classification: one-class vs. binary classifiers".INTERNATIONAL JOURNAL OF REMOTE SENSING 39.6(2018):1890-1910.