Non-uniform Compressive Sensing Imaging Based on Image Saliency

For more effective image sampling, compressive sensing (CS) imaging methods based on saliency have been proposed in recent years. Those assign higher measurement rates to salient regions, but lower rate non-salient regions improve the performance of CS imaging. However, those are block-based, which difficult apply actual as each photodiode should strictly correspond a block scene. In our work, we propose non-uniform method saliency, assigns density and where is number pixels measured unit size. As dimension signal reduced, quality reconstructed will be improved theoretically, confirmed by experiments. Since scene sampled whole, can easily applied sampling. To verify feasibility approach, design implement hardware sampling system, obtain measurements re-construct images. best knowledge, this first system saliency.