Differential Coded Aperture Single-Snapshot Spectral Imaging

We propose a novel concept of differential coded aperture snapshot spectral imaging (D-CASSI) technique exploiting the benefits of using {-1,+1} random mask, which is demonstrated by a broadband single-snapshot hyperspectral camera using compressed sensing. To double the information, we encode the image by two complementary random masks, which proved to be superior to two independent patterns. We utilize dispersed and non-dispersed encoded images captured in parallel onto a single detector. We explored several different approaches to processing the measured data, which demonstrates significant improvement in retrieving complex hyperspectral scenes. The experiments were completed by simulations in order to quantify the reconstruction fidelity. The concept of differential CASSI could be easily implemented also by multi-snapshot CASSI without any need for optical system modification.

Enhancement of CASSI by a zero-order image employing a single detector

Coded aperture snapshot spectral imaging (CASSI) makes it possible to recover 3D hyperspectral data from a single 2D image. However, the reconstruction problem is severely underdetermined and efforts to improve the compression ratio typically make the imaging system more complex and cause a significant loss of incoming light intensity. In this paper, we propose a novel approach to CASSI which enables capturing both spectrally sheared and integrated image of a scene with a single camera. We performed hyperspectral imaging of three different testing scenes in the spectral range of 500-900 nm. We demonstrate the prominent effect of using the non-diffracted image on the reconstruction of data from our camera. The use of the spectrally integrated image improves the reconstruction quality and we observed an approx. fivefold reduction in reconstruction time.