Abstract:
A non-sub sampled Contour let coefficient compressive sensing based on infrared and visible image fusion method was proposed to solve the problem that the infrared light sensor and the visible light sensor was failed to get clear images simultaneously in this study. Firstly, the multiscale and multi-directional image decomposition for the infrared and visible image was preformed by using the non-sub sampled Contourlet transformation and then the non-subsampled Contourlet coefficients of them were obtained. Secondly, the Low-frequency coefficients of the infrared and visible images was fused by the weighted average fusion method and the band-pass sub-band coefficients was fused by the pseudo-random Fourier matrix observations weights fusion method; Thirdly, the coefficient reconstruction for the fused band-pass sub-band coefficients was carried out. Finally, the image was reconstructed by the inverse non-subsampled Contourlet transformation. The experiment results showed that this fusion algorithm was failed to get image with clear object and background and it had the low computational complexity and good fusion effect.
Xin Feng, Xiaoming Wang, Jianwu Dang and Yu Shen, 2013. Fusion Method for Visible Light and Infrared Images Based on Compressive Sensing of Non-subsampled Contourlet Transformation Sparsity. Information Technology Journal, 12: 672-679.
Subscribe Today 
