基于互信息与梯度融合的多源图像匹配技术研究  

Multi-Modality Image Registration Techniques Based on Combined Mutual Information and Gradient Information

作　　者：毛璐璐[1] 徐刚锋[2] 陈显波[2] 

机构地区：[1]第二炮兵工程学院101教研室,陕西西安710025 [2]第二炮兵装备研究院,北京100085

出　　处：《红外技术》2009年第9期532-536,共5页Infrared Technology

摘　　要：对红外和可见光探测器获取同一场景的两幅图像进行配准融合,可增强对场景图像的理解和分析。互信息由于包含两图像灰度的熵和联合熵,可用于计算两图像灰度信息的相关性,适于作为多源图像匹配的测度。互信息匹配无需对图像进行预处理,但是,作为一种统计型测度,互信息忽略了图像像素间的空间信息,易陷入局部极值而出现误匹配。为此,文章提出了一种融合梯度信息的配准方法,同时考虑了两图像间的灰度统计相关性和像元灰度的局部空间变化信息,提高了多源图像匹配的精度和鲁棒性。最后通过实际图像进行匹配试验,验证了算法的正确性和有效性。Matching two images which are received by infrared and visible light seeker trom the same scene, can enhance comprehension and analysis of the images. Mutual information contains the entropy and the combined entropy of the gray value in the image, which can be used to calculate the relativity of the gray information between two images and is suitable for a measure of the multi-modality image registration. Image registration using mutual information does not need pre-processing of images. But as a statistical measure, Mutual information itself does not contain the spatial information, which usually causes mis-registration because of the local extremum. Therefore, the present paper proposes a registration method that includes spatial information by combining mutual information with a term based on the image gradient of the images to be registered. The method can improve precision and robustness of multi-modality image registration. At last, the experiment for practical image registration validates the correctness and validity of this method.

关 键 词：互信息 红外与可见光图像 梯度信息 图像配准 

分 类 号：TN911.73[电子电信—通信与信息系统]