A Branching Spatio-Spectral Dimensional Reduction Model for Hyperspectral Image Classification and Change Detection

In this paper, a branching convolutional encoder (BCE)-based spatio-spectral hyperspectral image dimensionality reduction model is presented. The architecture consists of a pointwise separable convolution to extract spectral features, and a two-dimensional convolution network to filter spatial features. Later, these two features are fused and fed into a decoder network which attempts to reconstruct the original image. This network is trained in a similar fashion to autoencoders, using a loss function to track the similarity between the original and the reconstructed image. Classification and change detection are important applications of hyperspectral images. The branching convolutional encoder is used together with classification and change detection models to demonstrate its feature representation performance – since the raw image has redundant features and poor interclass separability. The performance of the proposed dimensionality reduction model is compared with a spatial convolutional encoder and a densely-connected encoder. Classification accuracy reaches over 90% on all the datasets which out-performs the comparative methods. Moreover, the branching encoder’s representation power is observed with the change detection model as the rate of accuracy reaches over 99% for the Hermiston City-data. This research demonstrably presents the success of a branching convolutional dimensionality encoder for classification and change detection applications.