Open Access

ARTICLE

3D-CNNHSR: A 3-Dimensional Convolutional Neural Network for Hyperspectral Super-Resolution

Mohd Anul Haq^1,*, Siwar Ben Hadj Hassine², Sharaf J. Malebary³, Hakeem A. Othman⁴, Elsayed M. Tag-Eldin⁵

1 Department of Computer Science, College of Computer and Information Sciences Majmaah University, Almajmaah, 11952, Saudi Arabia
2 Department of Computer Science, College of Science and Arts at Muhayel, King Khalid University, Saudi Arabia
3 Department of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, P. O. Box 344, Rabigh, 21911, Saudi Arabia
4 Department of Mathematics, AL-Qunfudhah University College, Umm Al-Qura University, KSA, Saudi Arabia
5 Faculty of Engineering and Technology, Future University in Egypt, New Cairo, 11835, Egypt

* Corresponding Author: Mohd Anul Haq. Email:

Computer Systems Science and Engineering 2023, 47(2), 2689-2705. https://doi.org/10.32604/csse.2023.039904

Received 23 February 2023; Accepted 15 June 2023; Issue published 28 July 2023

Abstract

Hyperspectral images can easily discriminate different materials due to their fine spectral resolution. However, obtaining a hyperspectral image (HSI) with a high spatial resolution is still a challenge as we are limited by the high computing requirements. The spatial resolution of HSI can be enhanced by utilizing Deep Learning (DL) based Super-resolution (SR). A 3D-CNNHSR model is developed in the present investigation for 3D spatial super-resolution for HSI, without losing the spectral content. The 3D-CNNHSR model was tested for the Hyperion HSI. The pre-processing of the HSI was done before applying the SR model so that the full advantage of hyperspectral data can be utilized with minimizing the errors. The key innovation of the present investigation is that it used 3D convolution as it simultaneously applies convolution in both the spatial and spectral dimensions and captures spatial-spectral features. By clustering contiguous spectral content together, a cube is formed and by convolving the cube with the 3D kernel a 3D convolution is realized. The 3D-CNNHSR model was compared with a 2D-CNN model, additionally, the assessment was based on higher-resolution data from the Sentinel-2 satellite. Based on the evaluation metrics it was observed that the 3D-CNNHSR model yields better results for the SR of HSI with efficient computational speed, which is significantly less than previous studies.

---

Keywords

---