A Fast 3D CNN for Hyperspectral Image Classification
This work addresses the computational complexity and feature extraction challenges in hyperspectral image classification, which is important for applications like remote sensing, but it appears incremental as it builds on existing 3D CNN approaches.
The authors tackled hyperspectral image classification by proposing a fast 3D CNN model that processes overlapping 3D patches to utilize spatial-spectral information, achieving competitive performance on benchmark datasets like Pavia University, Salinas, and Indian Pines compared to state-of-the-art methods.
Hyperspectral imaging (HSI) has been extensively utilized for a number of real-world applications. HSI classification (HSIC) is a challenging task due to high inter-class similarity, high intra-class variability, overlapping, and nested regions. A 2D Convolutional Neural Network (CNN) is a viable approach whereby HSIC highly depends on both Spectral-Spatial information, therefore, 3D CNN can be an alternative but highly computational complex due to the volume and spectral dimensions. Furthermore, these models do not extract quality feature maps and may underperform over the regions having similar textures. Therefore, this work proposed a 3D CNN model that utilizes both spatial-spectral feature maps to attain good performance. In order to achieve the said performance, the HSI cube is first divided into small overlapping 3D patches. Later these patches are processed to generate 3D feature maps using a 3D kernel function over multiple contiguous bands that persevere the spectral information as well. Benchmark HSI datasets (Pavia University, Salinas and Indian Pines) are considered to validate the performance of our proposed method. The results are further compared with several state-of-the-art methods.