Comparative study of hyperspectral image classification by multidimensional Convolutional Neural Network approaches to improve accuracy

作者：

Highlights：

• Neural network architectures are presented to hyperspectral image classification.

• Multi-dimensional Convolutional Neural Network architectures are developed.

• The performance of the multi-dimensional architectures are evaluated and compared.

• We utilize Salinas and Pavia University hyperspectral data sets.

摘要

•Neural network architectures are presented to hyperspectral image classification.•Multi-dimensional Convolutional Neural Network architectures are developed.•The performance of the multi-dimensional architectures are evaluated and compared.•We utilize Salinas and Pavia University hyperspectral data sets.

论文关键词：Hyperspectral imaging,Deep learning,Convolutional neural networks,Hyperspectral image classification,Multi-dimensional CNN

论文评审过程：Received 10 June 2020, Revised 9 March 2021, Accepted 22 May 2021, Available online 29 May 2021, Version of Record 2 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115280