基于序贯相似性检测的NCC目标跟踪快速匹配方法  

Target tracking of NCC fast matching method based on sequential similarity detection

作　　者：邢藏菊[1] 温兰兰[1] 何苏勤[1] 

机构地区：[1]北京化工大学,北京100029

出　　处：《电子设计工程》2015年第3期187-190,共4页Electronic Design Engineering

摘　　要：基于特征点的图像匹配方法的关键是准确快速地将可靠的特征点提取出来。经典归一化互相关匹配法属于基于特征点匹配方法中的一种,归一化互相关匹配法具有操作简单,匹配精度高等优点,但其计算量庞大,难以满足实时跟踪的要求。提出了一种基于序贯相似性检测的归一化互相关快速匹配方法,并对提出的改进方法进行实验验证。实验表明,该方法可以准确快速的进行特征点匹配,减少了算法的计算时间,有效地减少了发生误匹配的概率。The feature points-based image matching is a key method of extracting reliable characteristic points. Although the conventional normalized cross correlation（NCC） method has the advantages of simple and high matching accuracy, it is difficult to meet real-time processing tracking requirements because of the amount of NCC algorithm. In this paper, we propose a novel NCC fast matching method that based on sequential similarity detection, and apply it to real-time tracking of the target image. Experimental results show that the algorithm carried out matching feature points quickly and accurately, reducing the computational time, and reducing the false match rate effectively.

关 键 词：归一化互相关 序贯相似性检测 图像匹配 目标跟踪 SSDA+NCC 

分 类 号：TN95[电子电信—信号与信息处理]