一种基于卡尔曼滤波的数字稳像算法  

A Kalman filter based digital image stabilization algorithm

作　　者：王仕海[1] 杨艳芳[2] 齐美彬[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009 [2]合肥工业大学电子科学与应用物理学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2014年第11期1317-1321,共5页Journal of Hefei University of Technology：Natural Science

基　　金：合肥工业大学重大项目预研资助项目(2010HGZY0003)

摘　　要：经典卡尔曼滤波算法对存在复杂有意扫描运动的视频进行数字稳像时,稳像后的图像帧会出现较大未定义区域,为了解决该问题,文章提出了一种改进的数字稳像算法,并采用块匹配法估计相邻两帧图像的全局运动矢量,使用卡尔曼滤波器对全局运动矢量进行滤波,构造表征未定义区域大小的偏差量,并与滤波器残差相加作为新的残差,根据偏差的大小及其变化,采用模糊控制的方法控制偏差值对新残差的影响。实验结果表明,该方法能够有效滤除视频中的高频和低频抖动噪声,同时明显减小稳像后视频帧的未定义区域。When using the classical Kalman filter based digital image stabilization algorithm to remove the jitter in the video with complex intentional scanning motion ,the image of the processed video of‐ten presents large undefined region .To solve this problem ,an improved digital image stabilization al‐gorithm is proposed .The block matching method is used to estimate the global motion vector between two adjacent frames .The global motion vector is filtered with Kalman filter ,and a deviation which can characterize the size of the undefined area is constructed and added to the residual of the filter as the new residual .T he impact of the residual on the new residual is controlled by fuzzy control method based on the size and speed of the deviation .T he experimental results show that this method can ef‐fectively filter out the high and low frequency jitter noise in the video ,significantly reducing the unde‐fined region of the image in the processed video .

关 键 词：数字稳像 块匹配法 未定义区域 卡尔曼滤波 模糊控制 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]