采用变分法的遥感影像条带噪声去除  

Stripe Noise Removal of Remote Images Based on Variation

作　　者：王昶[1,2] 王旭 纪松[2] WANG Chang;WANG Xu;JI Song(School of Civil Engineering, University of Science and Technology Liaoning, Anshan, Liaoning 114051, China;Institute of Surveying and Mapping, Information Engineering University, Zhengzhou 450001, China;Forestry Institute, Liaoning Forestry Vocation-Technical College, Shenyang 110101, China)

机构地区：[1]辽宁科技大学土木工程学院,辽宁鞍山114051 [2]信息工程大学地理空间信息学院,郑州450001 [3]辽宁林业职业技术学院林学院,沈阳110101

出　　处：《西安交通大学学报》2019年第3期143-149,共7页Journal of Xi'an Jiaotong University

基　　金：国家自然科学基金资助项目(41401534)

摘　　要：为了避免去除遥感影像条带噪声时丢失影像细节,构建了综合两种单向变分模型的组合去噪方法。首先,构建一种条带去除单向变分模型,通过此模型可以有效去除遥感影像条带噪声,从而初步获得近似遥感影像及条带噪声影像,同时避免近似遥感影像出现阶梯效应;其次,为了避免条带噪声影像中包含的少量细节信息丢失,构建一种条带保留单向变分模型,通过此模型可以去除条带噪声影像中的细节信息而只保留条带噪声,从而有效分离出细节信息;最后,把分离出的细节信息与近似遥感影像进行累加得到去噪影像。通过实验分析发现,本文方法不仅能完全去除条带噪声,而且基本没有破坏影像细节,去噪后的影像质量得到明显提高。To avoid the loss of image details when removing the stripe noise of remote images, a combined destriping method of two unidirectional variation models was constructed. First, a stripe removal unidirectional variation model which can effectively remove the stripe noise and obtain the approximate restoration images and stripe noise images was constructed, and the stair effect is avoided in approximate remote images. Second, in order to avoid losing details in the stripe noise image, a stripe preserve unidirectional variation model was constructed, which could remove the image details from the stripe noise image and only preserve the stripe noise, so that the stripe noise and the image details could be separated effectively. Finally, the approximate remote image and the image details were superimposed to obtain the destriped image. Experimental results show that the proposed method can effectively restrain the stripe noise of remote images, and preserve the details of the remote images very well, hence the quality of destriped images is improved obviously.

关 键 词：条带噪声影像 条带去除单向变分模型 条带保留单向变分模型 遥感影像 

分 类 号：P237[天文地球—摄影测量与遥感]