|
OALib Journal期刊
ISSN: 2333-9721
费用：99美元
|
|
|
|
基于SIFT特征的多帧图像超分辨重建
DOI: 10.11834/jig.20091129
Keywords: 超分辨,图像配准,SIFT,关键点,光流法,参考帧
Abstract:
精确的亚像素级图像配准是图像超分辨重建中的关键问题。在图像超分辨重建中广泛使用的基于像素特征的光流法，对于大幅度运动场的计算很难做到精确的亚像素级配准。本文考虑了一种基于SIFT(scaleinvariantfeaturetransform)特征的鲁棒性多帧图像超分辨重建算法。首先提取输入的低分辨待匹配图像对的SIFT关键点及其特征矢量，随后选取候选匹配关键点对，通过RANSAC(randomsampleconsensus)鲁棒方法去除奇异值，并根据假设的平移性几何约束模型，获得图像对的平移运动配准参数，然后选取视场中心对应的或指定的图像帧为初始参考帧，再使用传统的超分辨重建框架获得最终的重建结果。仿真实验结果表明，提出的基于SIFT特征的图像超分辨重建方案是有效的，超分辨重建的图像质量在主观评价和客观指标上都获得了优于经典算法的效果。
| [1] | 吴炜,杨晓敏,陈默,一种新颖的人脸图像超分辨率技术,光学精密工程,2008(05).
|
| [2] | Farsiu S,Robinson D,Elod M,Advances and challenges in super-resolution,International Journal of Imaging Systems and Technology,2004(02).
|
| [3] | Baker S,Matthews I,Lucas-Kanade 20 years on:A unifying framework,International Journal of Computer Vision,2004(03).
|
| [4] | Lowe D G,Distinctive image features from seale-invariant keypoints,International Journal of Computer Vision,2004(02).
|
| [5] | Farsin S.Robinson D.Milanfar P MDSP Resolution Enhancement Software 2009
|
| [6] | Wang Z,Bovik A C,Sheikh H R,Image quality assessment:from error visibility to structural similarity,IEEE Transactions on Image Processing,2004(04).
|
| [7] | Park S C,Park M K,Kang M G,Super-resolution image reconstruction:A technical overview,IEEE Signal Processing Magazine,2003(03).
|
| [8] | Yau A C,Bose N K,Ng M K,An efficient algorithm for superresolution in medium field imaging,Multidimensional Systems and Signal Processing,2007(2-3).
|
| [9] | 王润生,信息融合,北京:科学出版社,2007.
|
| [10] | Farsin S,Robinson M D,Elad M,Fast and robust multiframe super resolution,IEEE Transactions on Image Processing,2004(10).
|
| [11] | Zhao W Y,Sawhney S,Is super-resolution with optical flow feasible?,Copenhagen,Denmark,2000.
|
| [12] | Wang Z,Wu G,Sheikh H R,Quality-aware images,IEEE Transactions on Image Processing,2006(06).
|
Full-Text
|
|
Contact Us
service@oalib.com QQ:3279437679 
WhatsApp +8615387084133
|
|
