| On the Appropriate Feature for General SAR Image Registration | |
Li, Dong; Zhang, Yunhua ; Li, D (reprint author), Chinese Acad Sci, Ctr Space Sci & Appl Res, Key Lab Microwave Remote Sensing, 1 Nanertiao, Beijing 100190, Peoples R China.
| |
| Department | 微波遥感部 |
| Source Publication | SAR IMAGE ANALYSIS, MODELING, AND TECHNIQUES XII |
| 2012 | |
| Pages | 85360X |
| Language | 英语 |
| ISSN | 0277-786X |
| ISBN | 978-0-8194-9276-0 |
| Abstract | An investigation to the appropriate feature for SAR image registration is conducted. The commonly-used features such as tie points, Harris corner, the scale invariant feature transform (SIFT), and the speeded up robust feature (SURF) are comprehensively evaluated in terms of several criteria such as the geometrical invariance of feature, the extraction speed, the localization accuracy, the geometrical invariance of descriptor, the matching speed, the robustness to decorrelation, and the flexibility to image speckling. It is shown that SURF outperforms others. It is particularly indicated that SURF has good flexibility to image speckling because the Fast-Hessian detector of SURF has a potential relation with the refined Lee filter. It is recommended to perform SURF on the oversampled image with unaltered sampling step so as to improve the subpixel registration accuracy and speckle immunity. Thus SURF is more appropriate and competent for general SAR image registration.; An investigation to the appropriate feature for SAR image registration is conducted. The commonly-used features such as tie points, Harris corner, the scale invariant feature transform (SIFT), and the speeded up robust feature (SURF) are comprehensively evaluated in terms of several criteria such as the geometrical invariance of feature, the extraction speed, the localization accuracy, the geometrical invariance of descriptor, the matching speed, the robustness to decorrelation, and the flexibility to image speckling. It is shown that SURF outperforms others. It is particularly indicated that SURF has good flexibility to image speckling because the Fast-Hessian detector of SURF has a potential relation with the refined Lee filter. It is recommended to perform SURF on the oversampled image with unaltered sampling step so as to improve the subpixel registration accuracy and speckle immunity. Thus SURF is more appropriate and competent for general SAR image registration. |
| Keyword | Feature Detector Feature Descriptor Image Registration Speeded Up Robust Feature (Surf) Subpixel Accuracy Synthetic Aperture Radar (Sar) |
| Conference Name | Conference on SAR Image Analysis, Modeling and Techniques XII |
| Conference Date | SEP 26-27, 2012 |
| Conference Place | Edinburgh, SCOTLAND |
| Indexed By | EI ; CPCI |
| Document Type | 会议论文 |
| Identifier | http://ir.nssc.ac.cn/handle/122/3354 |
| Collection | 微波遥感部 |
| Corresponding Author | Li, D (reprint author), Chinese Acad Sci, Ctr Space Sci & Appl Res, Key Lab Microwave Remote Sensing, 1 Nanertiao, Beijing 100190, Peoples R China. |
| Recommended Citation GB/T 7714 | Li, Dong,Zhang, Yunhua,Li, D . On the Appropriate Feature for General SAR Image Registration[C]. BELLINGHAM:SPIE-INT SOC OPTICAL ENGINEERING,2012:85360X. |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| 201285360X.pdf（429KB） | 开放获取 | CC BY-NC-SA | Application Full Text | |||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment