基于压缩感知的加速近端梯度下降法

Descent-Accelerated Proximal Gradient Algorithm Based on Compressive Sensing

运用图像处理技术对卫星、侦察机和无人机侦察获取的图像进行校正和去噪等处理,可以提高战场环境影像和打击目标图像清晰度,有利于提升战场侦察监视效能。基于压缩感知技术能够以远小于奈奎斯特采样率从少量的测量值中重构出原信号的基本原理,提出了一种基于压缩感知的加速近端梯度下降(DAPG)图像去噪重构算法,并证明了该算法的收敛性。试验结果表明,与4种传统算法相比,该算法重构的图像有效提高了清晰度,其目标特征更加明显。

Using image processing technology to correct and denoise the images obtained by satellite,reconnaissance plane and unmanned aerial vehicle(UAV),the clarities of images about the battlefield environment and the striking targets are improved.It is conducive to improving the effectiveness of bat-tlefield reconnaissance and surveillance.Based on the principle that the compressed sensing technology can reconstruct the original signal from a small number of measured values at a sampling rate recon-struct much less than Nyquist,a denoising and reconstruction algorithm of the descent-accelerated proximal gradient(DAPG)images is proposed.The convergence of the algorithm is proved.Experi-mental results show that,compared with four traditional algorithms,the algorithm can effectively im-prove the image clarity,and the target feature is more obviously improved.