Abstract
Abstract. Hyperspectral image classification (HSIC) is a challenging task in remote sensing data analysis, which has been applied in many domains for better identification and inspection of the earth surface by extracting spectral and spatial information. The combination of abundant spectral features and accurate spatial information can improve classification accuracy. However, many traditional methods are based on handcrafted features, which brings difficulties for multi-classification tasks due to spectral intra-class heterogeneity and similarity of inter-class. The deep learning algorithm, especially the convolutional neural network (CNN), has been perceived promising feature extractor and classification for processing hyperspectral remote sensing images. Although 2D CNN can extract spatial features, the specific spectral properties are not used effectively. While 3D CNN has the capability for them, but the computational burden increases as stacking layers. To address these issues, we propose a novel HSIC framework based on the residual CNN network by integrating the advantage of 2D and 3D CNN. First, 3D convolutions focus on extracting spectral features with feature recalibration and refinement by channel attention mechanism. The 2D depth-wise separable convolution approach with different size kernels concentrates on obtaining multi-scale spatial features and reducing model parameters. Furthermore, the residual structure optimizes the back-propagation for network training. The results and analysis of extensive HSIC experiments show that the proposed residual 2D-3D CNN network can effectively extract spectral and spatial features and improve classification accuracy.
Highlights
Hyperspectral imaging has a wide variety of real-world applications, including land cover analysis, urban analysis, environmental and agricultural analysis, and anomaly identification
The results are compared with state-of-theart models such as support vector machine (SVM), random forest (RF), 2D-convolutional neural network (CNN), 3DCNN
Batch normalization (BN) and 50% of dropout are used to deal with the over-fitting problem
Summary
Hyperspectral imaging has a wide variety of real-world applications, including land cover analysis, urban analysis, environmental and agricultural analysis, and anomaly identification. Hyperspectral remote sensing classification is an effective way to distinguish different features and provide critical decision-making and reference information for different fields. Some advanced remote sensing platforms, such as airborne, space satellite, and UAV platforms, can achieve hyperspectral and high-resolution remote sensing data. Advanced machine learning algorithms such as support vector machine, decision tree, and random forest (RF) have the stability for the hyperspectral classification task. The support vector machine (SVM) seeks to separate two-class data by learning an optimal decision that separates the training samples in a kernel-included high dimensional feature space. Some studies using SVM for hyperspectral image classification can improve result performance (Mountrakis et al, 2011; Li, Bioucas-Dias & Plaza 2013; Song et al, 2020)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
