Multimedia acquisition and coding techniques have received increasing attention due
to the wide spread of multimedia telecommunication. Compressed Sensing (CS) is an
emerging signal processing technology that enables acquisition of signals that exhibit
sparsity in some basis, directly in a compressed manner. CS proves to be powerful for
energy constrained devices that benefit from processing at lower sampling rates. In
this paper, we propose a compressed sensing framework for images and video signals
that relies on an efficient perceptual-based weighting strategy. The proposed
compressed sensing strategy focuses the measurements and recovery on the most
perceptually pronounced coefficients of the underlying signal. Simulation results
demonstrate that the proposed framework provides significant improvement over
different CS systems.