A 3-Stage Spectral-Spatial Method for Hyperspectral Image Classification

被引:6
作者
Chan, Raymond H. [1 ,2 ]
Li, Ruoning [1 ]
机构
[1] City Univ Hong Kong, Dept Math, 83 Tat Chee Ave, Hong Kong, Peoples R China
[2] Hong Kong Ctr Cerebrocardiovasc Hlth Engn, 19 W Ave,Sci Pk, Hong Kong, Peoples R China
关键词
hyperspectral image classification; semi-supervised learning; nested sliding window; support vector machines; smoothed total variation; image reconstruction; SUPPORT VECTOR MACHINES;
D O I
10.3390/rs14163998
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Hyperspectral images often have hundreds of spectral bands of different wavelengths captured by aircraft or satellites that record land coverage. Identifying detailed classes of pixels becomes feasible due to the enhancement in spectral and spatial resolution of hyperspectral images. In this work, we propose a novel framework that utilizes both spatial and spectral information for classifying pixels in hyperspectral images. The method consists of three stages. In the first stage, the pre-processing stage, the Nested Sliding Window algorithm is used to reconstruct the original data by enhancing the consistency of neighboring pixels and then Principal Component Analysis is used to reduce the dimension of data. In the second stage, Support Vector Machines are trained to estimate the pixel-wise probability map of each class using the spectral information from the images. Finally, a smoothed total variation model is applied to ensure spatial connectivity in the classification map by smoothing the class probability tensor. We demonstrate the superiority of our method against three state-of-the-art algorithms on six benchmark hyperspectral datasets with 10 to 50 training labels for each class. The results show that our method gives the overall best performance in accuracy even with a very small set of labeled pixels. Especially, the gain in accuracy with respect to other state-of-the-art algorithms increases when the number of labeled pixels decreases, and, therefore, our method is more advantageous to be applied to problems with a small training set. Hence, it is of great practical significance since expert annotations are often expensive and difficult to collect.
引用
收藏
页数:22
相关论文
共 64 条
[1]   Hyperspectral Region Classification Using a Three-Dimensional Gabor Filterbank [J].
Bau, Tien C. ;
Sarkar, Subhadip ;
Healey, Glenn .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2010, 48 (09) :3457-3464
[2]   Spatial Filtering in DCT Domain-Based Frameworks for Hyperspectral Imagery Classification [J].
Bazine, Razika ;
Wu, Huayi ;
Boukhechba, Kamel .
REMOTE SENSING, 2019, 11 (12)
[3]   Weighted Generalized Nearest Neighbor for Hyperspectral Image Classification [J].
Bo, Chunjuan ;
Lu, Huchuan ;
Wang, Dong .
IEEE ACCESS, 2017, 5 :1496-1509
[4]   Distributed optimization and statistical learning via the alternating direction method of multipliers [J].
Boyd S. ;
Parikh N. ;
Chu E. ;
Peleato B. ;
Eckstein J. .
Foundations and Trends in Machine Learning, 2010, 3 (01) :1-122
[5]   Change Detection of Amazonian Alluvial Gold Mining Using Deep Learning and Sentinel-2 Imagery [J].
Camalan, Seda ;
Cui, Kangning ;
Pauca, Victor Paul ;
Alqahtani, Sarra ;
Silman, Miles ;
Chan, Raymond ;
Plemmons, Robert Jame ;
Dethier, Evan Nylen ;
Fernandez, Luis E. ;
Lutz, David A. .
REMOTE SENSING, 2022, 14 (07)
[6]   Composite kernels for hyperspectral image classification [J].
Camps-Valls, G ;
Gomez-Chova, L ;
Muñoz-Marí, J ;
Vila-Francés, J ;
Calpe-Maravilla, J .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (01) :93-97
[7]   Extreme Sparse Multinomial Logistic Regression: A Fast and Robust Framework for Hyperspectral Image Classification [J].
Cao, Faxian ;
Yang, Zhijing ;
Ren, Jinchang ;
Ling, Wing-Kuen ;
Zhao, Huimin ;
Marshall, Stephen .
REMOTE SENSING, 2017, 9 (12)
[8]   Spectral-Spatial Classification of Hyperspectral Imagery Using Support Vector and Fuzzy-MRF [J].
Chakravarty, Sumit ;
Banerjee, Madhushri ;
Chandel, Sonali .
INTELLIGENT, SECURE, AND DEPENDABLE SYSTEMS IN DISTRIBUTED AND CLOUD ENVIRONMENTS (ISDDC 2017), 2017, 10618 :151-161
[9]   Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing [J].
Chan, Aland H. Y. ;
Barnes, Chloe ;
Swinfield, Tom ;
Coomes, David A. .
REMOTE SENSING IN ECOLOGY AND CONSERVATION, 2021, 7 (02) :306-320
[10]   A two-stage method for spectral-spatial classification of hyperspectral images [J].
Chan, Raymond H. ;
Kan, Kelvin K. ;
Nikolova, Mila ;
Plemmons, Robert J. .
JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2020, 62 (6-7) :790-807