Infrared and visible images fusion using Compressed Sensing based on average gradient

Compressed Sensing (CS) has inspired significant interest due to its compressive capability and lack of complexity on the sensor side recently. In this paper, the potential application of compressed sensing (CS) principle in the image fusion for infrared (IR) and visible images is provided. A novel self-adaptive weighted fusion scheme based on average gradient of measurements to fuse IR and visible images is developed in the compressed domain of CS using the total variation optimization. Experimental results indicate that the proposed method has better subjective visual effect and objective evaluation performance.