基于颜色传递和对比度增强的夜视图像彩色融合

针对基于颜色传递夜视图像彩色融合算法存在的热目标不突出问题,提出一种基于颜色传递和对比度增强的彩色融合算法。该算法首先利用非线性扩散和迭代阈值分割方法提取出图像中的热目标,然后在HSI颜色空间利用热目标和灰度融合图像对颜色传递得到的初步彩色融合图像进行调整,接着将处理结果变换回RGB颜色空间,得到最终的融合图像。实验结果表明,利用该算法得到的融合图像不仅与人眼视觉感知习惯一致,而且显著增强了目标与背景的对比度,从而有效提高了目标的可探测性。

Night Vision Image Color Fusion Method Using Color Transfer and Contrast Enhancement

As the traditional color fusion algorithm based on color transfer has an issue that the hot target is not highlight, a kind of color fusion algorithm of infrared and low-level-light image based on color transfer and contrast enhancement is proposed. This algorithm uses nonlinear diffusion and the iterative threshold segmentation to extract the target image firstly. And then, it adjusts the initial color fusion image obtained by color transfer using thermal target and gray fusion image in the HSI space. Next, the resultant image is transformed back into RGB color space, thus the final fused image is obtained. Experimental results show that, the proposed method has the merit that the fused result is consistent with the habit of human vision perception, and makes the contrast of target region within the cluttered background more outstanding. And then target detectability can be improved by the method.