| 基于SIFT特征配准的多帧迭代盲解卷积算法 |
| |
| 引用本文： | 宋向,耿则勋,王洛飞,魏小峰.基于SIFT特征配准的多帧迭代盲解卷积算法[J].测绘科学,2011,36(6):109-111. |
| |
| 作者姓名： | 宋向 耿则勋 王洛飞 魏小峰 |
| |
| 作者单位： | 1. 信息工程大学测绘学院,郑州450052;75719部队,武汉430074
2. 信息工程大学测绘学院,郑州,450052 |
| |
| 基金项目： | 国家863计划项目(2006AA12Z110);国家自然科学基金(60778051);测绘学院硕士学位论文创新与创优基金 |
| |
| 摘 要： | 在未配准的情况下,多帧图像解卷积算法不能发挥其利用多帧图像信息互补的优势,针对这种情况,本文将基于SIFT特征配准的算法引入多帧图像解卷积算法中,这一做法克服了各帧影像之间相同位置不同细节像素之间的影响,有效地提高了复原图像的质量。实际观测数据的复原结果证明了本文思想的正确性,配准后图像的复原结果更加清晰,且体现出观测目标更多的细节信息。
|
| 关 键 词： | 大气湍流 湍流降质图像 尺度不变特征 图像复原 多帧图像解卷积 |
Multi-frame iterative blind deconvolution based on the SIFT feature registration |
| |
| SONG Xiang,GENG Ze-xun,WANG Luo-fei,WEi Xiao-feng.Multi-frame iterative blind deconvolution based on the SIFT feature registration[J].Science of Surveying and Mapping,2011,36(6):109-111. |
| |
| Authors: | SONG Xiang GENG Ze-xun WANG Luo-fei WEi Xiao-feng |
| |
| Institution: | ①(①Institute of Surveying and Mapping,Information Engineering University,Zhengzhou 450052,China;②Troops 75719,Wuhan 430074,China) |
| |
| Abstract: | Most of the current multi-frame restoration algorithms either utilize the multi-frame data simply by shift-and-add or take no account of the precise registration between frames.With unregistered frames,the complementary information about the identical details can not be effectively used and the restoration quality is also influenced.Even sometimes with the increase of frames,the result probably turns to be worse.This paper incorporated the SIFT feature registration into the multi-frame deconvolution,which could overcome the interaction artifacts induced by unregistered images between different detail pixels at the same location and improve the quality of the restored images effectively.The experiments proved the superiority of this algorithm.The restored image would be clearer and show more details. |
| |
| Keywords: | atmospheric turbulence turbulence degraded images scale invariant features image restoration multi-frame image deconvolution |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
