Compressive hyperspectral imaging via adaptive sampling and dictionary learning
This work addresses hyperspectral imaging efficiency for applications like remote sensing, but it is incremental as it builds on existing compressive sensing methods.
The paper tackled the problem of compressive hyperspectral imaging by proposing a new sampling strategy based on dictionary learning and SVD, resulting in significant improvement over conventional compressive sensing approaches, with enhanced reconstruction performance through matrix balancing.
In this paper, we propose a new sampling strategy for hyperspectral signals that is based on dictionary learning and singular value decomposition (SVD). Specifically, we first learn a sparsifying dictionary from training spectral data using dictionary learning. We then perform an SVD on the dictionary and use the first few left singular vectors as the rows of the measurement matrix to obtain the compressive measurements for reconstruction. The proposed method provides significant improvement over the conventional compressive sensing approaches. The reconstruction performance is further improved by reconditioning the sensing matrix using matrix balancing. We also demonstrate that the combination of dictionary learning and SVD is robust by applying them to different datasets.