基于非下采样变换的多源图像融合算法研究.docVIP

基于非下采样变换的多源图像融合算法研究 陈小林 王延杰 （中国科学院长春光机与物理所，长春市东南湖大路3888号） 摘　要：目的：针对红外与可见光图像的融合。方法：提出了一种基于非下采样Contourlet变换的图像融合算法。并针对低频子带系数和各带通方向子带系数分别提出了基于红外图像与可见光图像物理特征的加权平均系数选择方案和基于区域能量匹配的系数选择方案。即对低频子带系数和各带通方向子带系数提出了低频基于区域梯度信息、高频基于区域特征因子的加权与选择结合的图像融合算法。结果：实验结果表明，相对于基于像素的图像融合算法，本文的图像融合算法具有更高的融合性能。结论：非下采样Contourlet变换具有较快的运算速度，是一种更适合图像融合的MGA工具。 关键词：图像融合 多尺度几何分析 非下采样Contourlet变换 区域能量匹配 中图分类号：TP2 文献标识码：A Design of forest fire detection system based on embedded processing platform Chen Xiaolin Wang Yanjie （Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences） fusion of infrared and visible images. Method: Based on the nonsubsampled contourlet transform, a algorithm for are proposed. in which a ‘weighted averaging’ scheme based on the physical features of infrared and visible images and a selection principle based on the local energy matching are presented for the low frequency subband coefficients and the high frequency subband coefficients respectively. The algorithm different fusion rules for the target regions and the background regions are discussed thoroughly. Especially, when merging the background regions, a region salience measure based on the region directional entropy or region energy is employed according to the structure similarity of the corresponding regions between the infrared image and the visible image. Result: Experimental results show that this algorithm has higher fusion performance, relative to the image fusion algorithm based on pixel. Conclusion: The sampling Contourlet transform has under rapid speed, that is a more suitable for image fusion MGA tools. Key words：Image fusion Multiscale geometric analysis Nonsubsampled contourlet transform Regional energy matching 1　引言 图像融合就是综合处理多源图像和图像序列的技术，将来自不同数据源的多特征图像进行合并，从而得到一个包含被测物体信息更完整的图像，使融合结果图像更适合人的视觉和计算机视觉，或者更适合进一步的计算机图像处理(如图像分割、特征提取、场景监视、目标识别及目标检测等等)的需要[1]。 [2]。融合源图像可能是在同一个时间段来自多个传感器的图像，也可能是单个传感器在不同时间提供的图像序列，减少或抑制单一信息对被感知对象或环境解释中可能存在的多义性、不完整性、不确定性和误差，最大限度地利用各种信息源提供的信息