<p>Hyperspectral (HS) data are enriched with highly resourceful abundant spectral bands. However, analyzing and interpreting these ample amounts of data is a challenging task. Optimal spectral bands should be chosen to address the issue of redundancy and to capitalize on the absolute advantages of HS data. Partial informational correlation (PIC)-based band selection approach is proposed for feature selection-based classification of HS images. PIC measure appears to be more skillful compared to mutual information for estimation of nonparametric conditional dependency. In this proposed approach, HS narrow bands are selected in an innovative way utilizing the PIC. This approach is more efficient in terms of computational time and in generalizing the applicability of selected spectral bands. Further, these optimal spectral bands are used in the support vector machine (SVM) and random forest classifier for performance evaluation. The optimum performance is accomplished with SVM classifier, and the achieved average overall accuracies are 82.89%, 91.4%, and 91.29% for the Indian Pines, Pavia University, and Botswana datasets, respectively. The proposed band selection approach is compared with different state-of-the-art techniques. This methodology improves the classification performances compared to the existing techniques, and the advancement in performances is proven to be statistically significant.</p>
Convolutional Neural Network (CNN) has established as an effective deep learning model for hyperspectral image classification by considering both spectral and spatial information. In this study, the performance of two-dimensional (2D) CNN architecture is evaluated at hyperspectral and multispectral resolution. Two types of multispectral data are analyzed viz., original and transformed multispectral data. Hyperspectral bands are transformed to spectral resolution of multispectral bands by averaging the reflectances of specific hyperspectral narrow bands which are falling within the spectral ranges of multispectral bands. The well-known Pavia University dataset and a new dataset of Pear orchard are investigated in this study. In case of Pear orchard dataset, classification is performed with both types of multispectral data. All the experiments are carried out with the same 2D CNN architecture. In case of Pavia University dataset, hyperspectral and transformed multispectral data achieve OA(%) of 94.29±1.28 and 94.27±2.01 respectively considering 20% samples as training. In case of Pear orchard dataset, hyperspectral, multispectral and transformed multispectral data achieve OA(%) of 91.59±0.89, 88.65±1.35, and 93.24±0.16 respectively considering 20% samples as training. It is evident that transformed multispectral data, which comprises of inherent hyperspectral information, provides similar or better performance compared to hyperspectral data. Further, with the use of 3D CNN architecture, classification performance improves in case of Pavia University dataset, whereas it remains statistically similar in case of Pear orchard dataset. The present promising results illustrates the performance of CNN even in small dataset which is comparable to several published state-of-the art results on the same dataset.