Change Detection of Remote Sensing Images Based on Weighted Nonnegative Matrix Factorization

被引：2
|
作者：
Wu, Hui [1 ]
Li, Heng-Chao [1 ]
Yang, Gang [1 ]
Yang, Wen [2 ]
机构：
[1] Southwest Jiaotong Univ, Sichuan Prov Key Lab Informat Coding & Transmiss, Chengdu, Peoples R China
[2] Wuhan Univ, Sch Elect Informat, Wuhan, Peoples R China
来源：
2019 10TH INTERNATIONAL WORKSHOP ON THE ANALYSIS OF MULTITEMPORAL REMOTE SENSING IMAGES (MULTITEMP) | 2019年
基金：
中国国家自然科学基金;
关键词：
Change detection; remote sensing images; weighted nonnegative matrix factorization; sparse constraint; UNSUPERVISED CHANGE DETECTION;
D O I：
10.1109/multi-temp.2019.8866946
中图分类号：
TP7 [遥感技术];
学科分类号：
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要：
In this paper, a change detection method of multitemporal remote sensing (RS) images based on weighted nonnegative matrix factorization (WNMF) is proposed. Firstly, difference image is generated according to the different types of input images. Then, in order to effectively explore the change information in two original RS images, WNMF is applied to extract features from the resulting difference image, in which a new weight matrix is designed by using difference values of the corresponding pixels. In addition, sparse constraint based on l(1/2)-norm regularization is enforced into WNMF to learn sparser features. Finally, a binary change mask (CM) is achieved by partitioning the extracted features with the k-means clustering. Experimental results on two pairs of RS images demonstrate the effectiveness of the proposed algorithm.
引用
收藏
页数：4
相关论文
共 50 条
  • [1] UNSUPERVISED CHANGE DETECTION OF REMOTE SENSING IMAGES BASED ON SEMI-NONNEGATIVE MATRIX FACTORIZATION
    Li, Heng-Chao
    Longbotham, Nathan
    Emery, William J.
    [J]. 2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2014, : 1289 - 1292
  • [2] DEEP SEMI-NONNEGATIVE MATRIX FACTORIZATION BASED UNSUPERVISED CHANGE DETECTION OF REMOTE SENSING IMAGES
    Yang, Gang
    Li, Heng-Chao
    Yang, Wen
    Emery, William J.
    [J]. IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 4917 - 4920
  • [3] NONNEGATIVE TENSOR FACTORIZATION BASED FUSION FOR CHANGES DETECTION IN MULTIRESOLUTION REMOTE SENSING IMAGES
    Benkouider, Yasmine Kheira
    Benhalouche, Fatima Zohra
    Karoui, Moussa Sofiane
    Iftene, Meziane
    [J]. 2022 IEEE MEDITERRANEAN AND MIDDLE-EAST GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (M2GARSS), 2022, : 33 - 36
  • [4] Cloud removal in remote sensing images using nonnegative matrix factorization and error correction
    Li, Xinghua
    Wang, Liyuan
    Cheng, Qing
    Wu, Penghai
    Gan, Wenxia
    Fang, Lina
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2019, 148 : 103 - 113
  • [5] Change detection in remote sensing images based on manifold regularized joint non-negative matrix factorization
    Weidong Yan
    Xinxin Liu
    Jinhuan Wen
    Jinfeng Hong
    Sa Zhang
    Rui Zhao
    [J]. Earth Science Informatics, 2021, 14 : 1763 - 1776
  • [6] Change detection in remote sensing images based on manifold regularized joint non-negative matrix factorization
    Yan, Weidong
    Liu, Xinxin
    Wen, Jinhuan
    Hong, Jinfeng
    Zhang, Sa
    Zhao, Rui
    [J]. EARTH SCIENCE INFORMATICS, 2021, 14 (04) : 1763 - 1776
  • [7] WEIGHTED NONNEGATIVE MATRIX FACTORIZATION
    Kim, Yang-Deok
    Choi, Seungjin
    [J]. 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 1541 - 1544
  • [8] A remote sensing image fusion algorithm based on constrained nonnegative matrix factorization
    Wang, Zhongni
    Yu, Xianchuan
    Zhang, Libao
    [J]. CISP 2008: FIRST INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOL 4, PROCEEDINGS, 2008, : 672 - 676
  • [9] Weighted Normalized Mutual Information based Change Detection in Remote Sensing Images
    Aktar, M.
    Mamun, M. A.
    Hossain, M. A.
    Shuvo, M. S. R.
    [J]. PROCEEDINGS OF THE 2016 19TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY (ICCIT), 2016, : 257 - 260
  • [10] CONSTRAINED NONNEGATIVE MATRIX FACTORIZATION FOR HYPERSPECTRAL CHANGE DETECTION
    Erturk, Alp
    [J]. 2020 MEDITERRANEAN AND MIDDLE-EAST GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (M2GARSS), 2020, : 49 - 52
12345