Fusion technique for grey-scale visible light and infrared images based on non-subsampled contourlet transform and intensity-hue-saturation transform

摘要

An adaptive fusion technique based on non-subsampled contourlet transform (NSCT) and intensity-hue-saturation (IHS) transform is presented. First, the grey-scale visible light image is colourised by utilising a reference image, and then, the values of components I, H and S can be obtained via IHS transform, which can separate intensity information from spectrum information of the image. Second, multi-scale and multi-directional decompositions of the infrared image and the component I of the grey-scale visible light image are performed by NSCT. By adopting certain fusion rules, the lowfrequency and high-frequency components of the fused image can be achieved. Third, being the component I of the final fused image, the grey-scale fused image can be gained by the use of inverse NSCT. Finally, the red-green-blue colourised fused image is reconstructed by the inverse IHS. Experimental results show that the technique is effective.