基于Non_local means的时空联合视频降噪算法  

Algorithm of Spatio-temporal Combination Video Real-time Denoising Based on Non_local Means

作　　者：叶庆伟[1] 谢永昌[1] 狄红卫[1] 

机构地区：[1]暨南大学光电工程系

出　　处：《微型电脑应用》2012年第5期32-35,共4页Microcomputer Applications

基　　金：广州市科技计划重点项目(2011J4300037)

摘　　要：针对监控视频图像的特点,提出了一种有效的实时视频降噪算法。首先结合多帧图像采用基于Non_local means的运动检测方法自适应地区分图像的运动区域和静止区域,对静止区域采用时域加权均值滤波,对运动区域采用空域ANL滤波。充分利用了视频的时域、空域信息,在去除视频序列噪声的同时很好地保护了图像的细节。实验结果表明,提出的算法在不造成运动拖影的前提下,能够显著提高视频的信噪比和图像的主观质量。An efficient algorithm of video real-time denoising is proposed for the video surveillance syetem.By motion detection to multi-frame images based on Non_local means,this algorithm can adaptively distinguish the still regions and motion regions of vid-eo image.Temporal weighted average filter to the still regions and spatial ANL filter to the motion regions are used separately.Ex-perimental results show that because of fully utilizing the spatio-temporal information of the video sequences,the proposed algorithm can significantly improve the signal-to-noise ratio and the subjective image quality without movement ghosting.

关 键 词：Non_local MEANS 时空联合 运动检测 视频降噪 

分 类 号：TN911.73[电子电信—通信与信息系统]