文档介绍：图形与图像;201211072#修改稿
基于K-SVD的低信噪比WMSN视频图像稀疏去噪收稿日期:2012–10–15;修回日期:2012–12–22
*基金项目:国家自然科学基金项目(面向山区铁路异物侵限监测的压缩感知视频图像处理方法61261040)
通迅地址:330013江西省南昌市华东交通大学信息工程学院
Address: School of Information Engineering, East China Jiao Tong University, Nanchang, 330013, . China
罗晖,褚红亮,王世昌
(华东交通大学信息工程学院,江西南昌 330013)
摘要:无线多媒体传感器网络(Wireless Multimedia works,WMSN)因感知视频等信息的优势而被广泛应用,但受天气、光照等外因干扰,所采集视频图像常含有较为严重的噪声。因此在低信噪比条件下进行视频图像去噪是保证WMSN视频监测有效性和可靠性的关键。在分析WMSN视频图像特征的基础上,首先对其进行周期性采集、分帧及帧差等预处理;然后对关键帧运用K-SVD训练DCT冗余字典以充分稀疏表示图像特征,并采用基于残差比的改进型Batch-OMP实现关键帧去噪及重构;而对残差帧则基于DCT冗余字典进行稀疏去噪处理;最后,叠加去噪后的关键帧和残差帧,从而整体上实现低信噪比WMSN视频图像的去噪及重构。实验表明,本文算法能更加有效地、较为快速地滤除视频图像噪声,适用于低信噪比WMSN视频图像去噪。
关键词:稀疏去噪;K奇异值分解;残差比;低信噪比;无线多媒体传感器网络;
中图分类号: 文献标识码:A
Sparse denoising via K-SVD for WMSN video image in low SNR
LUO Hui, CHU Hong-liang, WANG Shi-chang
(School of Information Engineering, East China Jiao Tong University, Nanchang 330013, China)
Abstract: As a highly effective method of perceiving multimedia information, Wireless Multimedia works (WMSNs) has shown its potential in many areas. However, the outside interference in the monitoring environment leads severe noise to video images. Obviously, video image denoising es the key to ensuring the validity and reliability of WMSN video monitoring. To denoise WMSN video image, firstly analyze its features and make some pretreatment. Secondly, employ the K-SVD alg