TY - JOUR
T1 - 2SRS: Two-Stream Residual Separable Convolution Neural Network for Hyperspectral Image Classification
AU - Zahisham, Zharfan
AU - Lim, Kian Ming
AU - Koo, Voon Chet
AU - Chan, Yee Kit
AU - Lee, Chin Poo
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - Typically, hyperspectral image suffers from redundant information, data scarcity, and class imbalance problems. This letter proposes a hyperspectral image classification framework named a two-stream residual separable convolution (2SRS) network that aims to mitigate these problems. Principal component analysis (PCA) is first employed to reduce the spectral dimension of the hyperspectral image. Subsequently, the data scarcity and class imbalance problems are overcome via spatial and spectral data augmentations. A novel spectral data creation from image patches is proposed. The augmented samples are fed into the proposed 2SRS network for hyperspectral image classification. We evaluated the proposed method on three benchmark datasets, namely, 1) Indian Pines (IP); 2) Pavia University; and 3) Salinas Scene (SA). The proposed method achieved state-of-the-art performance in terms of overall accuracy (OA), average accuracy (AA), and Kappa coefficient (Kappa) for both 30% and 10% training set ratios.
AB - Typically, hyperspectral image suffers from redundant information, data scarcity, and class imbalance problems. This letter proposes a hyperspectral image classification framework named a two-stream residual separable convolution (2SRS) network that aims to mitigate these problems. Principal component analysis (PCA) is first employed to reduce the spectral dimension of the hyperspectral image. Subsequently, the data scarcity and class imbalance problems are overcome via spatial and spectral data augmentations. A novel spectral data creation from image patches is proposed. The augmented samples are fed into the proposed 2SRS network for hyperspectral image classification. We evaluated the proposed method on three benchmark datasets, namely, 1) Indian Pines (IP); 2) Pavia University; and 3) Salinas Scene (SA). The proposed method achieved state-of-the-art performance in terms of overall accuracy (OA), average accuracy (AA), and Kappa coefficient (Kappa) for both 30% and 10% training set ratios.
KW - Convolutional neural networks (CNNs)
KW - hyperspectral image classification
KW - remote sensing
KW - residual learning
KW - separable 2-D-CNN
UR - http://www.scopus.com/inward/record.url?scp=85148444590&partnerID=8YFLogxK
U2 - 10.1109/LGRS.2023.3241720
DO - 10.1109/LGRS.2023.3241720
M3 - Article
AN - SCOPUS:85148444590
SN - 1545-598X
VL - 20
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
M1 - 5501505
ER -