Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Fast Image Mosaic Based on Wavelet Transform for Remote Sensing

CHENG Yuan-hang1,XUE Ding-yu1,HAN Xiao-wei2(1.School of Information Science & Engineering,Northeastern University,Shenyang 110004,China;2.School of Information Engineering,Shenyang University,Shenyang 110044,China.)  
A method of serial fast image mosaic was put forward for the remotely sensed images provided from UAV(unmanned air vehicle),based on wavelet transform and matching of low-frequency images.According to the interior and exterior azimuthal elements of the remotely sensed imaging by UAV,the rectangular spatial transformation and second order linear interpolation are used to correct the images.The method proposed uses the wavelet transform to extract the low-frequency subimages and search the relevant area,thus obtaining the characteristic image as template.Then,the SSDA(sequential similarity detection algorithm) is introduced to perform the image matching computation and after analyzing the result,two images are mosaiked together.Simulation results showed that the algorithm presented greatly improves the operation speed with high precision and that it can be applied to real-time mosaiking of serial images obtained from UAV.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved