基于Non_local means的时空联合视频降噪算法

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。

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

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.