Compressive spectral imaging approach using adaptive coded apertures

The coded aperture snapshot spectral imager (CASSI) acquires three-dimensional spectral images with two-dimensional coded projection measurements. This paper proposes an adaptive design method of the coded apertures, according to a priori knowledge of the target scene, to improve sensing efficiency and imaging performance of the super-resolution CASSI system. The adaptive coded apertures are constructed from the nonlinear thresholding of the grayscale map of the scene. Theoretical proof is provided to demonstrate the superiority of the adaptive coded apertures over traditional random coded apertures. Improvement in reconstruction performance is also verified by a set of simulations based on different spectral data.