基于Shearlet变换的单波段遥感图像拼接技术研究  

Research on Single Band Remote Sensing Image Based on the Algorithm of Shearlet

作　　者：赵艳楠[1] 王霞[1] 

机构地区：[1]河北工业大学信息工程学院,天津300401

出　　处：《科学技术与工程》2014年第6期218-221,共4页Science Technology and Engineering

摘　　要：为了实现遥感图像的拼接,利用加速鲁棒性特征(speeded up robust features,SURF)算法来提取特征点进行粗匹配,并采用RANSAC算法减少特征点的误匹配,再估计出图像间的投影矩阵,特别是在进行图像融合过程中,提出采用能够充分地反应图像细节信息的Shearlet算法,并利用客观评价准则和基于小波变换得到的融合图像进行比较。实验证明,提出的算法充分利用了单波段遥感图像的全局信息,得到的拼接图像细节信息更加丰富,能够准确地实现遥感图像的拼接。Firstly,feature detection and pre-matching of images are done by using SURF algorithm.Secondly,the RANSAC algorithm is used to eliminate the mismatch as well as calculate the coordinate transformation matrix H between the two images.Finally,the Shearlet algorithm which can fully reflect the detail information of the image is used to achieve the fused image,and the objective evaluation criteria is used to evaluate the fused images with the ones that obtained by the wavelet.Experiment shows that the method can utilize the whole information of the single band remote sensing image that the mosaic image can be more detailed and accurately realize image mosaic.

关 键 词：图像拼接 加速鲁棒性(SURF)算法 RANSAC Shearlet 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]