归一化线性滤波对运动图像静态视点平滑模型  

Smoothing Model of Static Viewpoint of Moving Image Based on Normalized Linear Filtering

作　　者：陈思慧[1] 

机构地区：[1]广东海洋大学网络信息中心,广东湛江524088

出　　处：《计算机仿真》2016年第3期163-166,共4页Computer Simulation

基　　金：河南省软科学研究计划项目(132400410934;132400410927)

摘　　要：针对汽车处于高速运动状态的运动图像静态视点进行平滑处理时,采集过程中无法与汽车完全同步,造成汽车的特征像素分量在高速运动中丢失,产生像素运动噪声干扰。采用传统的方法无法解决汽车图像边缘高频特征干扰对图像像元灰度的影响,导致拼花处理后的图像质量低,效果差。提出采用归一化线性滤波的运动图像静态视点平滑处理方法。采集运动图像,建立静态视点平滑处理模型,对平滑处理的矩阵进行求解。将运动图像中的像素点进行平滑处理,并进行归一化线性滤波处理,获得像素新坐标值,从而得到清晰的平滑处理图像。实验结果表明,利用改进算法进行运动图像静态视点平滑处理,能够提高运动图像的质量。When the static viewpoint of image for a moving car in high speed is smoothly processed, the acquisi- tion process cannot be fully synchronized with the car, which will cause the characteristic pixel loss and produce pixel moving noise. Traditional methods cannot eliminate the influence of high frequency interference of car image edge characteristics on the gray level image pixels, lead to low quality of image processing. An image smoothing method of static viewpoint for moving car is presented based on the normalized linear filtering. The moving images are collected and a smoothing model of static viewpoint is set up, the smoothing matrix is solved. The pixels in the image are smoothly processed through the normalized linear filtering, new pixel coordinates are obtained, and the clear smoot- hing images are obtained. Experimental resuhs show that the proposed algorithm can improve the quality of moving images.

关 键 词：归一化线性滤波 运动图像静态视点 平滑模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]