基于匹配跟踪置信度的自适应对应像素距离图像匹配跟踪算法  

The Adaptive Corresponding Pixel Distance Measurement Image Matching Tracking Algorithm Based on the Matching Tracking Confidence Factor

作　　者：罗军[1] 江和平[1] 沈振康[1] 

机构地区：[1]国防科技大学电子科学与工程学院ATR重点实验室,湖南长沙410073

出　　处：《信号处理》2008年第1期72-77,共6页Journal of Signal Processing

摘　　要：本文结合最小绝对差度量(MAD)和(Hausdroff)距离度量两者的基本思想的优点,提出了一种新的对应像素距离相似性度量方法和自适应模板图像匹配跟踪算法,设计了帧间和帧内匹配跟踪置信度,提出了基于匹配跟踪置信度的自适应对应像素距离图像匹配跟踪算法。并对基于匹配跟踪置信度的自适应对应像素距离图像匹配跟踪算法的匹配跟踪性能进行分析,实验结果表明:该算法具有较强的抗噪、抗畸变能力和匹配跟踪稳定性,具有较高的匹配精度和匹配概率。The idea of the MAD is combined with the Hausdroff distance measurement in the paper,then a new corresponding pixel distance measurement（CPDM） image matching algorithm and an adaptive template image matching tracking algorithm is presented. The matching tracking confidence factor of among the frames and inner the frame is designed. The adaptive corresponding pixel distanee measurement image matching tracking algorithm based on the matching tracking confidence factor is presented, and the perform- anee of the algorithm is analyzed. The results show that the adaptive CPDM image matching algorithm based on the matching tracking confidence factor has character of the better probability, precision and robustness of registration in the noise, deformation and occlude.

关 键 词：图像匹配 自适应匹配跟踪 匹配跟踪置信度 Hausdorff距离度量 

分 类 号：TN953[电子电信—信号与信息处理] TP391.41[电子电信—信息与通信工程]