基于数据挖掘的光学遥感图像重建研究  

Research on optical remote sensing image reconstruction based on Data Mining

作　　者：周云飞 王金策 郑婷一 赵国飞 王一骐 赵艺 薛芳芳 袁若兰 ZHOU Yunfei;WANG Jince;ZHENG Tingyi;ZHAO Guofei;WANG Yiqi;ZHAO Yi;XUE Fangfang;YUAN Ruolan(Shanxi Institute of Energy,Jinzhong Shanxi 030600;Sichuan University,Chengdu 610065)

机构地区：[1]山西能源学院,山西晋中030600 [2]四川大学,成都610065

出　　处：《激光杂志》2022年第11期139-143,共5页Laser Journal

基　　金：山西省自然科学青年基金项目(No.20210302124551);山西省高等学校教学改革创新基金项目(No.J2021808);山西省自然科学青年基金项目。

摘　　要：在光学遥感图像成像过程中,受到多种因素的影响,图像信噪比低,生成光学遥感图像无法满足实际应用的要求,为了改善光学遥感图像质量,提出基于数据挖掘技术的光学遥感图像重建方法。首先分析光学遥感图像成像原理,设计光学遥感图像质量退化模型,然后采用小波变换方法对光学遥感图像进行去噪处理,提高光学遥感图像信噪比,最后提取光学遥感图像重建特征,并采用数据挖掘技术建立光学遥感图像重建模型,采用具体光学遥感图像进行了重建仿真实验,结果表明,本方法可以较好地描述光学遥感图像质量退化过程,光学遥感图像重建精度超过96%,而且光学遥感图像重建时间大约6 s,可以满足光学遥感图像向大规模发展方向的要求,实际应用价值很高。In the process of optical remote sensing image imaging, affected by many factors, the image signal-to-noise ratio is low, and the generation of optical remote sensing image can not meet the requirements of practical application. In order to improve the quality of optical remote sensing image, an optical remote sensing image reconstruction method based on data mining technology is proposed. Firstly, the imaging principle of optical remote sensing image is analyzed, and the quality degradation model of optical remote sensing image is designed. Then, the wavelet transform method is used to denoise the optical remote sensing image and improve the signal-to-noise ratio of optical remote sensing image. Finally, reconstruction features of optical remote sensing images are extracted, and the reconstruction model of optical remote sensing image is established by using data mining technology, and the reconstruction simulation experiment is carried out with specific optical remote sensing image. The results show that, the method can better describe the quality degradation process of optical remote sensing image. The reconstruction accuracy of optical remote sensing image is more than 96%, and the reconstruction time of optical remote sensing image is about 6 s, which can meet the requirements of large-scale development of optical remote sensing image, and has high practical application value.

关 键 词：光学技术 遥感图像 信噪比 数据挖掘 重建时间 

分 类 号：TN911[电子电信—通信与信息系统]