分块投影匹配在快速序列图像稳定中的应用研究  

Block Projection Match for Fast Sequence Image Stabilization

作　　者：卞志国[1] 金立左[1] 费树岷[1] 

机构地区：[1]东南大学自动化学院,南京210096

出　　处：《航空兵器》2010年第4期26-29,共4页Aero Weaponry

基　　金：航空科学基金(20080169003)

摘　　要：图像稳定常用于各类序列图像系统的预处理。本文提出一种基于分块投影匹配的快速序列图像稳定算法。该算法将待处理序列图像进行分块,通过投影匹配计算得到各对应分块的运动矢量,提出一种评价准则赋予各运动矢量相应权重,利用改进的随机一致参数估计方法得到全局运动模型参数。试验结果表明,与基于KLT、SIFT等特征点匹配的估计算法相比,在对估计精度没有较大影响的前提下,本文算法具有运算速度快、能实时应用的特点。Sequence image stabilization is often used in the pretreatment of many kinds of sequence image process system. A new sequence image stabilization framework based on block projection match is proposed in this paper. First the frame to be processed is divided into some blocks, then the motion vector to previous frame of every block is estimated with the algorithm of projection match, and the corresponding weight of each motion vector is assigned through a novel evaluation criteria. At last, the global motion model is acquired by an improved parameter estimation algorithm of RANSAC. Comparing with the algorithms such as KLT and SIFT, the experimental results show that the proposed algorithm can satisfy the requirements of real-time applications without major influence on the estimation accuracy.

关 键 词：图像稳定 投影匹配 随机一致参数估计 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]