基于四阶相关系数的 NSCT 域红外与可见光图像融合

摘要

采用非下采样 Contourlet 变换（NSCT）模型提出了基于四阶相关系数的红外与可见光图像融合方法。首先对融合图像进行多尺度和多方向分解；对于低频分量，充分考虑红外和可见光图像物理特性的差异，采用基于区域平均梯度的融合策略；对高频分量采用四阶相关系数匹配策略来选择合适的高频系数；最后对融合后的系数进行 NSCT 逆变换得到融合图像。实验结果表明，该融合算法能更好地保留目标信息，同时也显著地提高了图像的信息量，在主观视觉效果和客观评价方面具有较好的融合性能。%In this paper,a new method based on nonsubsampled contourlet transform (NSCT)is proposed to fuse the infrared image and the visible light image.Firstly,the NSCT is performed on the original images to obtain the sub-bands coefficient in different scales and various directions.Considering the physical characteristics of two original im-ages,fusion strategy based on the regional average gradient is used for the low frequency sub-band coefficients.For the high frequency sub-band coefficients,the fourth-order correlation coefficient match strategy is used to select the suitable high-frequency coefficients.Finally,the fused coefficients are reconstructed to obtain the fused image.The experiment results show that the proposed method performs better in keeping and improving the target information,and it has better fusion performance in subjective visual effect and objective evaluation.