A Fast Fusion Algorithm of Visible and Infrared Images

To improve both the quality and performance speed,a simple and fast fusion approach for night color vision images is presented in this paper.Firstly,the contrast of infrared and visible images to be fused is adjusted with local histogram equalization.Then the two enhanced images are fused into three components of an RGB image with a simple linear fusion strategy.To obtain false color images possessing a natural day-time color appearance,this paper proposes an approach which transferred color from the reference to the fused images in a simplified Lab space.In this way,inappropriate color mappings can be avoided and overall discrimination capabilities are enhanced.Experimental results based on two different data sets show that the final scene has a natural day-time color appearance and the fusion process is simple and fast.