摘要
针对电力视频监控图像中存在的噪声,结合压缩感知理论,采用基于过完备字典的稀疏表示方法进行去噪。使用噪声图像训练过完备字典,其中过完备字典的更新使用K-SVD算法,求解稀疏系数使用OMP算法,且根据算法的特点引入了Dice匹配准则来改进正交匹配追踪算法用于求解稀疏系数,最后重构去噪后的图像。Matlab仿真实验表明,对添加了不同标准差的高斯噪声的图像,文中方法具有良好的去噪效果,与目前常用的小波函数相比,能更好的降低图像中的高斯白噪声,并且在字典训练过程中直接使用视频拍摄的带噪声图像,即使没有原始的无噪声图像依然能够完成去噪任务。
We address the image de-nosing problem in the video surveillance system in smart grid,the approach is based on compressed sensing and sparse representation theory over over-complete dictionary. We train dictionary by noisy image,and use K-SVD algorithm to update dictionary and OMP to compute sparse representation coefficients.An improved orthogonal matching pursuit algorithm based on atomic matching criterion of Dice coefficient is used to reconstruct images. Finally,we can get the de-noised image. The Matlab simulation experiments show that this method is an effective de-noising algorithm,and the de-noising result for Gaussian white noise is better than the wavelet functions. Using the video images which is corrupted to train the dictionary,while the de-noising task could be completed efficiently even there is no high-quality original image.
出处
《电测与仪表》
北大核心
2016年第18期10-13,40,共5页
Electrical Measurement & Instrumentation
关键词
压缩感知
稀疏表示
去噪
K-SVD
compressed sensing
sparse representation
de-noising
K-SVD