Image fusion based on HMSD and improved saliency detection
Aiming at the problem that different characteristics of visible images and infrared images may results in less prominent targets,low contrast,and more artifacts in fused image,a fusion method of infrared and visible images based on hybrid multi-scale decomposition and improved saliency detection is proposed.The infrared and visible light are decomposed into different feature levels by using the edge preserving property of gradient guided filter and the smoothing property of Gaussian filter.Different fusion strategies are adopted for images at different levels,and an improved saliency detection is used for fusion at the base level.The fused image reconstructed by combining fused sub-images of each level has prominent targets and clear backgrounds.Experimental results show that the proposed method has higher fusion quality and better visual effects compared to other typical fusion algorithms.
NETL
NSTL
万方数据
维普
