前下视红外图像中复杂地面背景下的目标定位

对于地面背景较复杂条件下的目标定位问题，目标模板匹配算法是一种有效的方法。将隐马尔科夫统计模型引入到目标模板匹配，并结合离散余弦变换，给出了一种图像相似性测度。采用真实的中波红外图像验证了该相似性度量的性能。实验结果表明，该测度适用于红外图像的模板匹配问题；且该相似性测度对噪声不敏感，优于常用的以相关系数为测度的方法。

Target position through FILR with complicated earth background

FLIR mainly treats with the objects such as bridges, airdromes and big buildings etc, which are based on complicated background on earth. An efficient method for positioning this kind of targets is template matching. In this paper a similarity measure for template matching is presented by using hidden Markov model and discrete cosine transform. Real mid-wave infrared images are used to evaluate the performance of the proposed similarity measure. The results show that this measure can be adopted for FLIR target position. Another characteristic of this measure is that it is not sensitive to noise level comparing with general measure based on correlation coefficient.