Semi-supervised SVM for individual tree crown species classification

被引:50
作者
Dalponte, Michele [1 ,2 ]
Ene, Liviu Theodor [2 ]
Marconcini, Mattia [3 ]
Gobakken, Terje [2 ]
Naesset, Erik [2 ]
机构
[1] Fdn E Mach, Res & Innovat Ctr, Dept Sustainable Agroecosyst & Bioresources, I-38010 San Michele All Adige, TN, Italy
[2] Norwegian Univ Life Sci, Dept Ecol & Nat Resource Management, NO-1432 As, Norway
[3] German Aerosp Ctr DLR, Wessling, Germany
关键词
Tree species classification; Semi-supervised classification; Hyperspectral data; SVM; Individual tree crowns; BOREAL FORESTS; IMAGE CLASSIFICATION; LIDAR DATA;
D O I
10.1016/j.isprsjprs.2015.10.010
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
In this paper a novel semi-supervised SVM classifier is presented, specifically developed for tree species classification at individual tree crown (ITC) level. In ITC tree species classification, all the pixels belonging to an ITC should have the same label. This assumption is used in the learning of the proposed semi-supervised SVM classifier (ITC-S3VM). This method exploits the information contained in the unlabeled ITC samples in order to improve the classification accuracy of a standard SVM. The ITC-S3VM method can be easily implemented using freely available software libraries. The datasets used in this study include hyperspectral imagery and laser scanning data acquired over two boreal forest areas characterized by the presence of three information classes (Pine, Spruce, and Broadleaves). The experimental results quantify the effectiveness of the proposed approach, which provides classification accuracies significantly higher (from 2% to above 27%) than those obtained by the standard supervised SVM and by a state-of-the-art semi-supervised SVM (S3VM). Particularly, by reducing the number of training samples (i.e. from 100% to 25%, and from 100% to 5% for the two datasets, respectively) the proposed method still exhibits results comparable to the ones of a supervised SVM trained with the full available training set. This property of the method makes it particularly suitable for practical forest inventory applications in which collection of in situ information can be very expensive both in terms of cost and time. (C) 2015 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.
引用
收藏
页码:77 / 87
页数:11
相关论文
共 50 条
[41]   Semi-Supervised Classification based on Gaussian Mixture Model for remote imagery [J].
XIONG Biao1 ;
2 State Key Laboratory of Remote Sensing Science .
Science China Technological Sciences, 2010, (S1) :85-90
[42]   Semi-Supervised Classification based on Gaussian Mixture Model for remote imagery [J].
Xiong Biao ;
Zhang XiaoJun ;
Jiang WanShou .
SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2010, 53 :85-90
[43]   Semi-Supervised Classification Based on Low Rank Representation [J].
Hou, Xuan ;
Yao, Guangjun ;
Wang, Jun .
ALGORITHMS, 2016, 9 (03)
[44]   Collaborative Representation Graph for Semi-Supervised Image Classification [J].
Guo, Junjun ;
Li, Zhiyong ;
Mu, Jianjun .
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2015, E98A (08) :1871-1874
[45]   Robust semi-supervised classification for imbalanced and incomplete data [J].
Chen, Mengxing ;
Dou, Jun ;
Fan, Yali ;
Song, Yan .
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2023, 45 (02) :2781-2797
[46]   Semi-Supervised Classification via Local Spline Regression [J].
Xiang, Shiming ;
Nie, Feiping ;
Zhang, Changshui .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (11) :2039-2053
[47]   Semi-supervised classification based on subspace sparse representation [J].
Guoxian Yu ;
Guoji Zhang ;
Zili Zhang ;
Zhiwen Yu ;
Lin Deng .
Knowledge and Information Systems, 2015, 43 :81-101
[48]   Combinative hypergraph learning for semi-supervised image classification [J].
Wei, Binghui ;
Cheng, Ming ;
Wang, Cheng ;
Li, Jonathan .
NEUROCOMPUTING, 2015, 153 :271-277
[49]   Semi-supervised Learning for Mars Imagery Classification and Segmentation [J].
Wang, Wenjing ;
Lin, Lilang ;
Fan, Zejia ;
Liu, Jiaying .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 19 (04)
[50]   Semi-supervised classification based on subspace sparse representation [J].
Yu, Guoxian ;
Zhang, Guoji ;
Zhang, Zili ;
Yu, Zhiwen ;
Deng, Lin .
KNOWLEDGE AND INFORMATION SYSTEMS, 2015, 43 (01) :81-101