基于分离信息熵的红外图像匹配方法

An Infrared Image Matching Method Based on Separating Information Entropy

利用红外图像匹配方法实现对目标的有效识别是现代战争中实现精确打击的主要手段。为了实现红外图像高性能匹配,文章提出了采用图像预处理的方法增强图像中的细节信息,通过互信息熵实现图像匹配,设计了由粗匹配到精匹配的算法流程,实现了算法的加速;通过将图像信息贫乏区进行分离处理的方法,优化了图像匹配算法的性能。实验结果表明,在进行红外图像匹配时,算法实时性和正确性得到有效提高。

The effective recognition of targets using infrared image matching methods is the main means of achieving precise strikes in modern warfare.In order to achieve high-performance matching of infrared images,the article proposes using image preprocessing to enhance the detail information in the image,achieving image matching through mutual information entropy,designing an algorithm flow from coarse matching to fine matching,and achieving algorithm acceleration;The performance of the image matching algorithm was optimized by separating and processing areas with poor image information.The experimental results show that the real-time performance and accuracy of the algorithm are effectively improved during infrared image matching.