测绘学报 ›› 2018, Vol. 47 ›› Issue (3): 348-358.doi: 10.11947/j.AGCS.2018.20170258

• 摄影测量学与遥感 • 上一篇    下一篇

融合引导滤波和迁移学习的薄云图像中地物信息恢复算法

胡根生1,2,3, 周文利1,2, 梁栋1,2, 鲍文霞1,2,3   

  1. 1. 安徽大学计算智能与信号处理教育部重点实验室, 安徽 合肥 230039;
    2. 安徽大学电子信息工程学院, 安徽 合肥 230601;
    3. 偏振光成像探测技术安徽省重点实验室, 安徽 合肥 230031
  • 收稿日期:2017-05-16 修回日期:2017-12-27 出版日期:2018-03-20 发布日期:2018-03-29
  • 通讯作者: 梁栋 E-mail:dliang@ahu.edu.cn
  • 作者简介:胡根生(1971-),男,博士,教授,研究方向为机器学习、遥感图像处理等。E-mail:hugs2906@sina.com
  • 基金资助:
    国家自然科学基金(61672032;61401001);偏振光成像探测技术安徽省重点实验室开放基金(2016-KFKT-003)

Information Recovery Algorithm for Ground Objects in Thin Cloud Images by Fusing Guide Filter and Transfer Learning

HU Gensheng1,2,3, ZHOU Wenli1,2, LIANG Dong1,2, BAO Wenxia1,2,3   

  1. 1. Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei 230039, China;
    2. School of Electronics and Information Engineering, Anhui University, Hefei 230601, China;
    3. Anhui Key Laboratory of Polarization Imaging Detection Technology, Hefei 230031, China
  • Received:2017-05-16 Revised:2017-12-27 Online:2018-03-20 Published:2018-03-29
  • Supported by:
    The National Natural Science Foundation of China (Nos. 61672032;61401001);The Open Fund of Anhui Key Laboratory of Polarization Imaging Detection Technology (No. 2016-KFKT-003)

摘要: 薄云覆盖遥感图像使图像上的地物信息模糊。本文给出了一种融合引导滤波和迁移学习的薄云图像中地物信息恢复算法。首先利用多方向非抽样对偶树复小波变换对薄云目标图像和无云引导图像进行多分辨率分解,再对分解后的低频子带分别进行支持向量引导滤波和迁移学习,对分解后的高频子带利用修正的Laine增强函数进行增强,然后应用基于区域能量的选择和加权相结合的方法对引导滤波输出和迁移学习模型预测的低频子带进行融合,最后对增强后的高频子带和融合后的低频子带进行多方向非抽样对偶树复小波逆变换重构,获得地物信息恢复图像。Landsat-8 OLI多光谱图像的试验结果表明,支持向量引导滤波能够有效保留目标图像的地物细节信息,域自适应的迁移学习能有效扩展可利用的多源多时相遥感图像范围,通过融合引导滤波和迁移学习能有效去除遥感图像上的薄云,获得较好的地物信息恢复效果。

关键词: 遥感图像, 信息恢复, 图像融合, 引导滤波, 迁移学习

Abstract: Ground object information of remote sensing images covered with thin clouds is obscure. An information recovery algorithm for ground objects in thin cloud images is proposed by fusing guide filter and transfer learning. Firstly, multi-resolution decomposition of thin cloud target images and cloud-free guidance images is performed by using multi-directional nonsubsampled dual-tree complex wavelet transform. Then the decomposed low frequency subbands are processed by using support vector guided filter and transfer learning respectively. The decomposed high frequency subbands are enhanced by using modified Laine enhancement function. The low frequency subbands output by guided filter and those predicted by transfer learning model are fused by the method of selection and weighting based on regional energy. Finally, the enhanced high frequency subbands and the fused low frequency subbands are reconstructed by using inverse multi-directional nonsubsampled dual-tree complex wavelet transform to obtain the ground object information recovery images. Experimental results of Landsat-8 OLI multispectral images show that, support vector guided filter can effectively preserve the detail information of the target images, domain adaptive transfer learning can effectively extend the range of available multi-source and multi-temporal remote sensing images, and good effects for ground object information recover are obtained by fusing guide filter and transfer learning to remove thin cloud on the remote sensing images.

Key words: remote sensing image, information recovery, image fusion, guided filter, transfer learning

中图分类号: