| 基于Shearlet变换与区域分割的遥感图像融合 |
| |
| 引用本文： | 张惊雷,胡晓婷,温显斌. 基于Shearlet变换与区域分割的遥感图像融合[J]. 光电子．激光, 2015, 26(12): 2393-2399 |
| |
| 作者姓名： | 张惊雷 胡晓婷 温显斌 |
| |
| 作者单位： | 天津理工大学 自动化学院天津市复杂系统控制理论及应用重点实验室 ,天津 300384;天津理工大学 自动化学院天津市复杂系统控制理论及应用重点实验室 ,天津 300384;天津理工大学 计算机视觉与系统教育部重点实验室,天津 300384 |
| |
| 基金项目： | 国家自然科学基金(61472278)资助项目 (1.天津理工大学 自动化学院天津市复杂系统控制理论及应用重点实验室 ,天津 300384； 2.天津理工大学 计算机视觉与系统教育部重点实验室,天津 300384) |
| |
| 摘 要： | 结合区域分割理论,提出了一种基于Shearlet变换 的遥感图像融合算法。首先通过色度H-亮度I-饱和度S(HI S) 变换对多光谱图像进行分解,将I分量与全色图像进行Shearlet变换,得到低 频、高频信息图；然后对 低频信息图进行基于灰度的区域分割,两图像的低频部分使用改进的加权融合算法改善融 合图像轮廓模 糊问题,以区域匹配度作为融合规则,高频分量采用区域清晰比作为融合规则,得到更多 的细节信息； 最后通过HIS逆变换得到融合图像。实验结果表明,本文算法 所得融合图像在有效地保持了多光谱图像光谱信息的同时,提高了空间细节信息。
|
| 关 键 词： | Shearlet变换 区域分割 图像融合 遥感图像 |
| 收稿时间： | 2015-08-02 |
Remote sensing image fusion algorithm based on Shearlet transform and region seg mentation |
| |
| ZHANG Jing-lei,HU Xiao-ting and WEN Xian-bin. Remote sensing image fusion algorithm based on Shearlet transform and region seg mentation[J]. Journal of Optoelectronics·laser, 2015, 26(12): 2393-2399 |
| |
| Authors: | ZHANG Jing-lei HU Xiao-ting WEN Xian-bin |
| |
| Affiliation: | Tianjin Key Laboratory for Control Theory & Applications in Complicated Syst ems,School of Electrical Engineering,Tianjin University of Technology,Tianjin 300384,China;Tianjin Key Laboratory for Control Theory & Applications in Complicated Syst ems,School of Electrical Engineering,Tianjin University of Technology,Tianjin 300384,China;Key Laboratory of Computer Vision and System,Ministry of Educatio n of China,Tianjin University of Technology,Tianjin 300384,China |
| |
| Abstract: | A remote sensing image fusion method based on Shearlet transform and region segmentation is propo sed.First,the multi-spectral image is transformed into hue-intensity-saturation (HIS) color space.The intensity component of the multi-spectral image and the panchromatic image are decompose d by Shearlet transform to obtain low frequency and high frequency information images.Second,the low freque ncy parts of multi-spectral image are segmented into regions by means of thresholds method. The results show that the proposed algorithm can not only retain the spectrum in formation source by the multi-spectral image,but also improve the spatial detail information. |
| |
| Keywords: | Shearlet transform region segmentation image fusion remote sensing image |
|
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
