改进的密集连接网络遥感图像超分辨重建

遥感图像超分辨增加了遥感图像的细节信息,在遥感图像处理中有重要的地位。为了进一步提高遥感图像超分辨的重建效果,本文提出一种改进的密集连接网络遥感图像超分辨重建算法。首先对基于残差网络的深度超分辨算法(VDSR)进行改进,结合密集连接网络(DenseNet),将残差网络中的残差块替换成密集块,并且添加一组密集层与瓶颈层,实现DenseNet网络结构的改进,同时,修改网络激活函数为PReLU函数,网络训练采用L1损失函数。为了使网络在遥感图像上具有更好的效果,训练网络时,数据集全部采用遥感图像作为训练样本。当训练的epoch达到了大约35次时网络已经收敛。实验结果表明,与VDSR算法相比,本文改进的算法对遥感图像的效果更优,峰值信噪比(PSNR)平均增加了1.05 dB,结构相似度(SSIM)平均增加了0.042。     

An improved image blind deblurring based on dark channel prior

In order to solve the ringing effect caused by the incorrect estimation of the blur kernel, an improved blind image deblurring algorithm based on the dark channel prior is proposed. First, in the blur kernel estimation stage, high-pass filtering is introduced to enhance the image quality and enhance the edge information to make the blur kernel estimation more accurate. A combination of super Laplacian prior and dark channel prior is introduced to estimate the potential clear image. Then the accurate blur kernel is estimated through alternate iterations from coarse to fine. In the image restoration stage, a weighted least square filter is introduced to suppress the ringing effect of the original clear image to further improve the quality of image restoration. Finally, image deconvolution based on Laplace priors and L₀ regularized priors is used to restore clear images. Experimental results show that our approach improves the peak signal-to-noise ratio(PSNR) by about 0.4 d B and structural similarity(SSIM) by about 0.01, respectively. Compared with the existing image deblurring algorithms, this method can estimate the blur information more accurately, so that the restored image can achieve the effect of keeping the edges and removing ringing.