A Fast and Compact 3-D CNN for Hyperspectral Image Classification

• Published in: IEEE geoscience and remote sensing letters Vol. 19; pp. 1 - 5
• Main Authors: Ahmad, Muhammad, Khan, Adil Mehmood, Mazzara, Manuel, Distefano, Salvatore, Ali, Mohsin, Sarfraz, Muhammad Shahzad
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3-D convolutional neural network (CNN); Accuracy; Artificial neural networks; Classification; Computational efficiency; Computational modeling; Computer applications; Computing time; Data mining; Dimensions; Feature extraction; Feature maps; hyperspectral images (HSIs); Hyperspectral imaging; Image classification; Kernel; kernel function; Kernel functions; Model accuracy; Neural networks; Performance enhancement; Solid modeling; Spatial data; Spatial resolution; Spectra; Three dimensional models; Two dimensional models
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2020.3043710

Hyperspectral images (HSIs) are used in a large number of real-world applications. HSI classification (HSIC) is a challenging task due to high interclass similarity, high intraclass variability, overlapping, and nested regions. The 2-D convolutional neural network (CNN) is a viable classification approach since HSIC depends on both spectral-spatial information. The 3-D CNN is a good alternative for improving the accuracy of HSIC, but it can be computationally intensive due to the volume and spectral dimensions of HSI. Furthermore, these models may fail to extract quality feature maps and underperform over the regions having similar textures. This work proposes a 3-D CNN model that utilizes both spatial-spectral feature maps to improve the performance of HSIC. For this purpose, the HSI cube is first divided into small overlapping 3-D patches, which are processed to generate 3-D feature maps using a 3-D kernel function over multiple contiguous bands of the spectral information in a computationally efficient way. In brief, our end-to-end trained model requires fewer parameters to significantly reduce the convergence time while providing better accuracy than existing models. The results are further compared with several state-of-the-art 2-D/3-D CNN models, demonstrating remarkable performance both in terms of accuracy and computational time.