Compressed sampling reconstruction of hyperspectral images based on spectral prediction

Abstract

With increasing amounts of hyperspectral images (HSI) and the limitations of the memory requirements, compressive techniques for hyperspectral images have attracted extensive research efforts in recent years. The main difficulty of applying compressed sampling (CS) theory to compression and reconstruction of hyperspectral images lies in using the spatial correlation and spectral correlation of hyperspectral images. In this paper, a reconstruction algorithm of hyperspectral images taking advantage of two‐dimensional compressed sampling (2DCS) and two‐dimensional total variation (2DTV) incorporating spectral prediction (SP) is investigated. In the sampling process, the hyperspectral images are divided into reference bands and common bands, and all bands are sampled using 2DCS independently. In the reconstruction process, the reference bands are reconstructed by 2DTV first. In order to improve the reconstruction quality of common bands, spectral prediction utilizing the spectral correlation between reference bands and common bands is conducted. Then the spectral compensation is computed by using a combination of the prediction value and the initial approximation for the common bands. The residual between the compensation value and the original value is obtained to revise the approximation for the common bands. The algorithm is implemented in an iterative manner to enhance the performance. Experimental results on popular hyperspectral datasets reveal that the proposed algorithm exploiting spectral prediction outperforms the algorithm 2DCS‐2DTV, which does not use spectral correlation, as well as the state‐of‐the‐art algorithms in terms of peak signal‐to‐noise ratio (PSNR). In particular, when the sampling rate of the reference bands is higher than that of the common bands, the proposed algorithm would improve the reconstruction quality dramatically. © 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Survey on compressed sensing reconstruction method for 3D data

“…Wang et al 11 proposed a spectral prediction reconstruction algorithm using a 2DCS and 2DTV constraint. The algorithm first averages the entire HSI in groups, with each group consisting of a reference band and a subset of non‐reference bands, and all bands are sampled independently in the sampling stage.…”

Data Adaptable Sparse Reconstruction for Hyperspectral Image Recovery from Compressed Measurements

“…Apart from using conventional image compression algorithms [5] for image compression, it is sensible to use compressive sensing [6] techniques to perform compression. The reason being, CS greatly increases the compression performance and also reduces the computational process at the encoder side.The Hyperspectral image compression and reconstruction methods based on compressive sensing makes use of either spatial and spectral information separately [7] or combination of spectral and spatial information. Gaussian i.i.d.…”

Compressed sensing reconstruction of hyperspectral images jointly using spatial smoothing feature and spectral correlation

“… to exploit the structure of HSIs, and the three‐dimensional compressed sampling that decreases the spectral correlation. Meanwhile, prediction methods making use of the spectral correlation have been put forward for HSIs, such as the interband prediction , bidirectional spectral prediction , and multihypothesis (MH) prediction .…”