Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification

被引:11
作者
Zhao, Chunhui [1 ,2 ]
Qin, Boao [1 ,2 ]
Feng, Shou [1 ,2 ]
Zhu, Wenxiang [1 ,2 ]
机构
[1] Harbin Engn Univ, Coll Informat & Commun Engn, Harbin 150001, Peoples R China
[2] Harbin Engn Univ, Key Lab Adv Marine Commun & Informat Technol, Minist Ind & Informat Technol, Harbin 150001, Peoples R China
基金
中国国家自然科学基金;
关键词
hyperspectral image classification; superpixel segmentation; graph learning; sparse representation; multiscale fusion; SUBSPACE; FUSION; KERNEL; CNN;
D O I
10.3390/rs14030681
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Hyperspectral image classification (HSIC) methods usually require more training samples for better classification performance. However, a large number of labeled samples are difficult to obtain because it is cost- and time-consuming to label an HSI in a pixel-wise way. Therefore, how to overcome the problem of insufficient accuracy and stability under the condition of small labeled training sample size (SLTSS) is still a challenge for HSIC. In this paper, we proposed a novel multiple superpixel graphs learning method based on adaptive multiscale segmentation (MSGLAMS) for HSI classification to address this problem. First, the multiscale-superpixel-based framework can reduce the adverse effect of improper selection of a superpixel segmentation scale on the classification accuracy while saving the cost to manually seek a suitable segmentation scale. To make full use of the superpixel-level spatial information of different segmentation scales, a novel two-steps multiscale selection strategy is designed to adaptively select a group of complementary scales (multiscale). To fix the bias and instability of a single model, multiple superpixel-based graphical models obatined by constructing superpixel contracted graph of fusion scales are developed to jointly predict the final results via a pixel-level fusion strategy. Experimental results show that the proposed MSGLAMS has better performance when compared with other state-of-the-art algorithms. Specifically, its overall accuracy achieves 94.312%, 99.217%, 98.373% and 92.693% on Indian Pines, Salinas and University of Pavia, and the more challenging dataset Houston2013, respectively.
引用
收藏
页数:23
相关论文
共 56 条
[1]   SLIC Superpixels Compared to State-of-the-Art Superpixel Methods [J].
Achanta, Radhakrishna ;
Shaji, Appu ;
Smith, Kevin ;
Lucchi, Aurelien ;
Fua, Pascal ;
Suesstrunk, Sabine .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) :2274-2281
[2]   Deep Learning for Classification of Hyperspectral Data [J].
Audebert, Nicolas ;
Le Saux, Bertrand ;
Lefevre, Sebastien .
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE, 2019, 7 (02) :159-173
[3]  
Bai Xue, 2017, IEEE Transactions on Geoscience and Remote Sensing, V55, P5093, DOI 10.1109/TGRS.2017.2702197
[4]   3-D Deep Learning Approach for Remote Sensing Image Classification [J].
Ben Hamida, Amina ;
Benoit, Alexandre ;
Lambert, Patrick ;
Ben Amar, Chokri .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (08) :4420-4434
[5]   A Multi-Objective Particle Swarm Optimization for Trajectory Planning of Fruit Picking Manipulator [J].
Cao, Xiaoman ;
Yan, Hansheng ;
Huang, Zhengyan ;
Ai, Si ;
Xu, Yongjun ;
Fu, Renxuan ;
Zou, Xiangjun .
AGRONOMY-BASEL, 2021, 11 (11)
[6]  
Chen M., 2021, COMPUT ELECTRON AGR, V187, P106237, DOI [10.1016/j.compag.2021.106237, DOI 10.1016/j.compag.2021.106237]
[7]   Superpixel-Based Extended Random Walker for Hyperspectral Image Classification [J].
Cui, Binge ;
Xie, Xiaoyun ;
Ma, Xiudan ;
Ren, Guangbo ;
Ma, Yi .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (06) :3233-3243
[8]   Sparse Representation-Based Hyperspectral Image Classification Using Multiscale Superpixels and Guided Filter [J].
Dundar, Tugcan ;
Ince, Taner .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2019, 16 (02) :246-250
[9]   Evaluation of hyperspectral remote sensing as a means of environmental monitoring in the St. Austell China clay (kaolin) region, Cornwall, UK [J].
Ellis, RJ ;
Scott, PW .
REMOTE SENSING OF ENVIRONMENT, 2004, 93 (1-2) :118-130
[10]   Classification of Hyperspectral Images by Exploiting Spectral-Spatial Information of Superpixel via Multiple Kernels [J].
Fang, Leyuan ;
Li, Shutao ;
Duan, Wuhui ;
Ren, Jinchang ;
Benediktsson, Jon Atli .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (12) :6663-6674