Semisupervised Classification of Remote Sensing Images With Hierarchical Spatial Similarity

被引:29
|
作者
Huo, Lian-Zhi [1 ]
Tang, Ping [1 ]
Zhang, Zheng [1 ]
Tuia, Devis [2 ]
机构
[1] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Beijing 100101, Peoples R China
[2] Ecole Polytech Fed Lausanne, Lab Geog Informat Syst, CH-1015 Lausanne, Switzerland
基金
瑞士国家科学基金会;
关键词
Image classification; image segmentation; kernel methods; support vector machines (SVMs); COMPOSITE KERNELS;
D O I
10.1109/LGRS.2014.2329713
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
A semisupervised kernel deformation function, including spatial similarity, is proposed for the classification of remote sensing (RS) images. The method exploits the characteristic of these images, in which spatially nearby points are likely to belong to the same class. To fulfill this assumption, a kernel encoding both spatial and spectral proximity using unlabeled samples is proposed. In this letter, two similarity functions for constructing a spatial kernel are proposed. Experimental tests are performed on very high-resolution multispectral and hyperspectral data. With respect to state-of-the-art semisupervised methods for RS images, the proposed method incorporating spatial similarity obtains higher classification accuracy values and smoother classification maps.
引用
收藏
页码:150 / 154
页数:5
相关论文
共 50 条
  • [21] Scene classification of remote sensing images based on hierarchical sparse coding
    Xu Jiaqing
    Lv Qi
    Liu Hongjun
    He Jie
    JOURNAL OF ENGINEERING-JOE, 2018, (16): : 1650 - 1657
  • [22] Retrieval of remote sensing images based on semisupervised deep learning
    Zhang H.
    Liu X.
    Yang S.
    Li Y.
    Li, Yu (liyu@radi.ac.cn), 1600, Science Press (21): : 406 - 414
  • [23] A novel semisupervised SVM for pixel classification of remote sensing imagery
    Maulik, Ujjwal
    Chakraborty, Debasis
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2012, 3 (03) : 247 - 258
  • [24] A novel semisupervised SVM for pixel classification of remote sensing imagery
    Ujjwal Maulik
    Debasis Chakraborty
    International Journal of Machine Learning and Cybernetics, 2012, 3 : 247 - 258
  • [25] Semisupervised Center Loss for Remote Sensing Image Scene Classification
    Zhang, Jun
    Zhang, Min
    Pan, Bin
    Shi, Zhenwei
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2020, 13 : 1362 - 1373
  • [26] Semisupervised Scene Classification for Remote Sensing Images: A Method Based on Convolutional Neural Networks and Ensemble Learning
    Dai, Xueyuan
    Wu, Xiaofeng
    Wang, Bin
    Zhang, Liming
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2019, 16 (06) : 869 - 873
  • [27] One-class Classifier Ensemble based Enhanced Semisupervised Classification of Hyperspectral Remote Sensing Images
    Singh, Pangambam Sendash
    Singh, Vijendra Pratap
    Pandey, Manish Kumar
    Karthikeyan, Subbiah
    2020 INTERNATIONAL CONFERENCE ON EMERGING SMART COMPUTING AND INFORMATICS (ESCI), 2020, : 22 - 27
  • [28] Spatial contextual classification of remote sensing images using a Gaussian process
    Sun, Shujin
    Zhong, Ping
    Xiao, Huaitie
    Wang, Runsheng
    REMOTE SENSING LETTERS, 2016, 7 (02) : 131 - 140
  • [29] A hierarchical learning paradigm for semi-supervised classification of remote sensing images
    Alhichri, Haikel
    Bazi, Yacoub
    Alajlan, Naif
    Ammour, Nassim
    2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 4388 - 4391
  • [30] A class-driven hierarchical ResNet for classification of multispectral remote sensing images
    Weikmann, Giulio
    Perantoni, Gianmarco
    Bruzzone, Lorenzo
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXIX, 2023, 12733