Compressive spectral image classification using 3D coded convolutional neural network
This addresses data acquisition and processing challenges in remote sensing for hyperspectral images, though it appears incremental as it builds on existing compressive sensing and deep learning approaches.
The paper tackled hyperspectral image classification by developing a 3D coded convolutional neural network that operates directly on compressive measurements from coded-aperture snapshot spectral imagers, improving classification accuracy without full data cube reconstruction, with results assessed as superior to state-of-the-art methods on several datasets.
Hyperspectral image classification (HIC) is an active research topic in remote sensing. Hyperspectral images typically generate large data cubes posing big challenges in data acquisition, storage, transmission and processing. To overcome these limitations, this paper develops a novel deep learning HIC approach based on compressive measurements of coded-aperture snapshot spectral imagers (CASSI), without reconstructing the complete hyperspectral data cube. A new kind of deep learning strategy, namely 3D coded convolutional neural network (3D-CCNN) is proposed to efficiently solve for the classification problem, where the hardware-based coded aperture is regarded as a pixel-wise connected network layer. An end-to-end training method is developed to jointly optimize the network parameters and the coded apertures with periodic structures. The accuracy of classification is effectively improved by exploiting the synergy between the deep learning network and coded apertures. The superiority of the proposed method is assessed over the state-of-the-art HIC methods on several hyperspectral datasets.