基于空间特性的自适应Retinex变分校正模型

Adaptive Retinex Variational Model Based on Spatial Information for the Uneven Intensity Correction

提出了一种基于空间特性的自适应Retinex变分校正模型,用于遥感影像的亮度不均校正。该模型构建逐像素的权重函数,能够根据不同的空间信息自适应地控制反射分量的TV正则化约束的强度,在影像的边缘处施加较小的TV正则化约束保持影像的边缘特征;而在影像的同质区域,施加较大的TV正则化约束强度;同时为了防止局部曝光过度,根据反射分量的物理性质,采用均值逼近灰度中值约束"GW"准则。实验表明,提出的自适应方法不仅能够匀光校正,还能保持影像的空间信息;与Kimmels和Lis方法相比,自适应方法在视觉比较结果和量化评估比较中,都具有一定的优势。

Adaptive retinex variational model based on spatial information for the uneven intensity correction of remote sensing images is proposed. An adaptive regularization weight parameter based on spatial information is used to constrain TV regularization strength. In the edges,weak regularization strength is enforced to preserve detail,and in the homogeneous areas,strong regularization strength is enforced to eliminate the uneven intensity. Also,the'gray world'(GW)assumption based on the physical characteristics of reflectance is used to avoid overexposed regions. Finally,experimental results demonstrate the proposed method can correct uneven intensity distribution and preserve details. Compared to Kimmels method and Lis method,the proposed method is better,based on the visual effect and quantitative assessments.