Deblurring Texture Extraction from Digital Aerial Image by Reforming “Steep Edge” Curve

Texture extract from digital aerial image is widely used in three-dimensional city modeling to generate “photo-realistic” views. In this paper, a method based on reforming “Steep edge” curve, which clearly explains how the diffraction of the sunlight makes digital aerial image blurring, is proposed to deblur the texture extraction from digital aerial image, and the experiment shows a good result in visualization and automation.     

Deblurring Texture Extraction from Digital Aerial Image by Reforming "Steep Edge" Curve

Texture extract from digital aerial image is widely used in three-dimensional city modeling to generate "photo-realistic" views. In this paper, a method based on reforming "Steep edge" curve, which clearly explains how the diffraction of the sunlight makes digital aerial image blurring, is proposed to deblur the texture extraction from digital aerial image, and the experiment shows a good result in visualization and automation.     

去除DMSP/OLS影像模糊的RTSVD算法

DMSP/OLS作为最早的夜光遥感数据具有很大的应用价值,解决该数据存在的模糊问题,能够大幅提高数据质量。本文分析模糊原因,提出了一种结合Pct影像发光频率滤波的正则化截断奇异值分解（RTSVD）算法,该算法能有效消除影像模糊现象并保留影像真实信息。首先考虑到光源像素发光频率必定高于非光源像素,利用Pct影像中的像素发光频率排除平均灯光影像中的非光源像素,然后利用L曲线求得正则化截断奇异值分解的截断参数,以此对影像进行分解重组。试验表明,结合Pct影像发光频率滤波的正则化截断奇异值分解法可在保留影像信息的基础上去除模糊现象。     

水下图像基于 GAN 去模糊的增强技术

由于水下环境具有不稳定性,水下图像可能会出现偏色、对比度低以及运动模糊等退化现象。针对这些问题,本文提出了适用于水下图像的增强算法,其实现需要依次经过颜色恢复和去模糊这2个阶段。在第一阶段中,本文增强算法先利用高斯滤波和均值漂移对图像进行锐化;然后,通过对比图像各颜色通道的均值得到补偿值对图像颜色进行校正;最后通过线性拉伸来调整图像的对比度。在第二阶段中,采用带有残差思想的生成对抗网络(GenerativeAdversarialNetworks,GAN),利用9个连续的残差网络能够很好地提取图像中的特征,可起到消除模糊和增强图像特征的作用。利用本文算法处理水下图像时,发现本文方法不仅能去除图像模糊,而且能消除图像的色偏现象且不携带红色伪影。同时,通过对比水下图像质量度量(UnderwaterImageQualityMeasures,UIQM)和水下彩色图像质量评估(UnderwaterColorImageQualityEvaluation,UCIQE)这2项指标发现,本文算法有较好的图像处理效果。