基于多尺度top-hat分解的红外与可见光图像增强融合

Infrared and visible image features enhancement and fusion using multi-scale top-hat decomposition

提出了基于数学形态学与尺度空间理论相结合的特征增强融合算法。首先对源图像使用多尺度top-hat变换构造塔形分解的亮、暗细节特征和近似图像,再对源图像对应尺度的亮、暗细节特征应用融合规则,最后依据不同应用需求加权各尺度亮、暗特征得到融合图像。实验表明:文中算法能有效融合并增强源图像细节特征,消除红外源图像因对比度低、灰度值范围较窄、视觉效果模糊等对融合质量的不利影响,并能根据应用需求获得具有不同增强效果的融合图像,从而达到更好的视觉效果,提高融合图像的目标检测和识别能力。

To efficiently enhance fused images in visible and infrared image fusion process, a novel image fusion algorithm using multi-scale top-hat decomposition was proposed. Firstly, multi-scale bright and dim salient features of the source images were extracted iteratively through top-hat transform using structuring elements with the same shape and increasing sizes. Then these multi-scale bright and dim features were combined by fusion rule. Finally, the enhanced fused image was obtained by weighting the bright and dim features according to specific requirements. Experimental results on infrared and visible images and other multi-sensor images fusion from different applications using different fusion algorithms verified that the proposed algorithm could efficiently and simultaneously fuse and enhance the salient features of source images, and produce better visual effects and target detection or identification capabilities.