A hybrid classification method with dual-channel CNN and KELM for hyperspectral remote sensing images. Issue 1 (2nd January 2023)

• Record Type: Journal Article
• Authors: Zhao, Huimin; Wang, Chenchen; Chen, Huayue; Chen, Tao; Deng, Wu
• Is Part Of: International journal of remote sensing. Volume 44:Issue 1(2023)
• Page Start: 289
• Page End: 310
• Publication Date: 2023-01-02
• Subjects: hyperspectral remote sensing image classification -- dual-channel convolutional neural network -- principal component analysis -- local binary pattern -- kernel extreme learning machine; Remote sensing -- Periodicals; Télédétection -- Périodiques; 621.3678
• DOI: 10.1080/01431161.2022.2162352
• Languages: English
• ISSNs: 0143-1161

Abstract

ABSTRACT: In this paper, a hybrid classification method based on dual-channel convolutional neural network (DC-CNN) and kernel extreme learning machine (KELM), namely PLDC-KELM, is proposed to improve the spatial-spectral feature extraction ability and hyperspectral remote sensing image (HRSI) classification accuracy. In the proposed PLDC-KELM, principal component analysis (PCA) is employed to reduce the dimensionality of original HRSI, and local binary pattern (LBP) is utilized to extract spatial features from the data after dimensionality reduction, and the one-dimensional convolutional neural network (1D-CNN) model is constructed to extract deep spatial features from the dimensionality-reduced spatial features. The secure connection layers of two 1D-CNN models are connected to fuse deep spectral and spatial features. Finally, the fused features are input into KELM in order to realize an HRSI classification method. Indian Pines data, Pavia University data, and Salinas data are used to prove the effectiveness of the PLDC-KELM. The experimental results show that the PLDC-KELM method can achieve classification accuracy of 99.95%, 99.98%, and 99.97%, respectively. It is an effective method for hyperspectral remote sensing image classification.