Hyperspectral Band Selection Based on Deep Convolutional Neural Network and Distance Density

• Published in: IEEE geoscience and remote sensing letters Vol. 14; no. 12; pp. 2365 - 2369
• Main Authors: Zhan, Ying, Hu, Dan, Xing, Haihua, Yu, Xianchuan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.12.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 1-D convolution; Artificial neural networks; band selection; convolutional neural network (CNN); Data augmentation; Data models; deep learning; Distance; distance density (DD); Feature extraction; Hidden Markov models; hyperspectral imagery; Hyperspectral imaging; Methods; Neural networks; Retraining; Training
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2017.2765339

In this letter, a band-selection approach based on the deep convolutional neural network (CNN) and distance density (DD) is proposed. This method effectively mitigates the curse of dimensionality for hyperspectral images (HSIs). First, we use the hyperspectral full-band data to train a custom 1-D CNN to obtain a well-trained model. Second, we select band combinations based on DD. Using the rectified linear unit, which is the activation function of the CNN that is only activated with a nonzero value, we can effectively test the band combinations without retraining the model. Finally, the method selects the band combinations with the highest precision as the final selected bands. This precision measure is a new criterion for band selection. To further improve the performance, a data augmentation method based on DD is also proposed. To justify the effectiveness of the proposed method, experiments are conducted on two HSIs. The results show that the proposed method can acquire more satisfactory results than traditional methods.