基于局部交叉熵的图像匹配跟踪算法  

Image matching tracking algorithm based on local cross-entropy

作　　者：江和平[1] 沈振康[1] 

机构地区：[1]国防科技大学ATR实验室,湖南长沙410073

出　　处：《红外与激光工程》2005年第6期729-732,共4页Infrared and Laser Engineering

摘　　要：交叉熵值的大小反映了模板图像与实时图像之间的信息量差异大小,从平均意义上来表征模板图像与实时图像之间的信息量差异量。为了解决机载成像光电吊舱系统中的图像辐射失真和几何失真问题,提出了基于局部交叉熵的图像匹配跟踪算法。由于交叉熵值最小准则有利于信息量丰富的图像匹配,因此该算法不仅具有抗噪能力,而且具有良好的抗辐射失真和抗几何失真的能力。仿真试验表明:在辐射失真情况下,该算法具有稳健的匹配跟踪能力,适应能力强,是一种很实用的匹配跟踪算法。The cross-entropy value illuminates the information difference between the template image and the real-time image on the average. In this paper, aiming at solving the problem of the radiation distortion and geometry distortion in the system of the photoelectric pod, the image matching tracking algorithm based on cross-entropy is proposed. Since the cross-entropy minimum rule is propitious to image matching with abundant information, the algorithm mentioned is provided with the very good antinoise properties, and the capability of resisting radiation distortion and geometry distortion.The results of simulation experiment show that this algorithm has steady matching tracking ability and well adaptability when radiation distortion happens. So it is a practical algorithm.

关 键 词：图像匹配 交叉熵 图像跟踪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]