Journal
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
Volume 13, Issue -, Pages 4133-4148Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2020.3008949
Keywords
Feature extraction; Convolution; Dimensionality reduction; Hyperspectral imaging; Training; Principal component analysis; Cubic convolutional neural network (Cubic-CNN); dimensionality reduction; hyperspectral image (HSI) classification; spatial-spectral features
Categories
Funding
- Natural Science Foundation of China [61971233, 61672291, 61972206, 61672293]
- Ministry of Education
- PAPD fund
- Engineering Research Center of Digital Forensics
Ask authors/readers for more resources
Recently, the hyperspectral image (HSI) classification methods based on convolutional neural networks (CNN) have developed rapidly with the advance of deep learning (DL) techniques. In order to more efficiently extract spatial and spectral features, we propose an end-to-end cubic CNN (Cubic-CNN) in this article. The proposed Cubic-CNN is a supervised DL framework that significantly improves classification accuracy and shortens training time. Specifically, Cubic-CNN employs the dimension reduction method combined with principal component analysis and 1-D convolution to remove redundant information from HSIs. Then, convolutions are performed on the planes in different directions of the feature cube data to fully extract spatial and spatial-spectral features and fuse the features from different dimensions. In addition, we performed batch normalization on the data cube after each convolutional layer to improve the performance of the network. Extensive experiments and analysis on standard datasets show that the proposed algorithm can outperform the existing state-of-the-art DL-based methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available