基于NSSCC的快速多波段图像配准算法  

Fast multi-spectral image registration based on NSSCC

作　　者：汪炜[1] 王伟[1] 濮运辰[1] 

机构地区：[1]上海交通大学自动化系,上海200240

出　　处：《计算机应用》2011年第1期167-169,174,共4页journal of Computer Applications

摘　　要：归一化互相关(NCC)方法是图像配准中使用非常广泛的方法,经典的NCC方法是基于空间域的,适用于单波段图像配准。但在实际应用中,往往要对多波段图像进行配准,此时NCC方法很可能无法获得正确的结果。最近有学者提出了归一化空间频谱互相关(NSSCC)方法,该方法可将多波段图像中不同波段的信息应用到图像配准中,与经典的NCC方法相比能够有效地提升配准的有效性。然而,如果图像所含波段较多且尺寸较大,NSSCC方法需要很大的计算量。结合标准的NCC快速算法,可以对NSSCC方法作进一步的改进。Among the methods for image registration, the Normalized Cross Correlation （NCC） method is the most widely used one, which is conceptually straightforward and easy to implement. The classic NCC method is based on spatial domain, works for single band image and does not leverage the spectral information of all spectral bands of images. A new normalized Spatial-Spectral Cross Correlation （NSSCC） method was proposed recently by some researchers, which utilizes all spectral bands for multi-spectral image registration. This NSSCC method effectively increases the registration reliability and discrimination compared to the classic NCC method. However, if the image contains many spectral bands and its size is large, the NSSCC method will require high computation cost. This paper presented an improved ＇algorithm for fast calculation of the NSSCC method and its application to the problem of multi-spectral image registration. The simulation results show that the improved algorithm can effectively reduce the computation cost of the NSSCC method.

关 键 词：多波段图像配准 归一化空间频谱互相关 归一化互相关 模板匹配 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]