Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Engineering of Surveying and Mapping》 2017-11
Add to Favorite Get Latest Update

Matching method for oblique aerial image assisted by DEM

CHANG Yue;DENG Fei;LI Tianshuo;School of Geodesy & Geomatics,Wuhan University;Collaborative Innoation Center for Territorial Sovereignty and Maritime Rights,Wuhan University;  
In the oblique aerial photogrammetry,the oblique images have large geometric deformation due to the great differences of the viewing angles.However,the algorithm with affine scaling invariance like ASIFT algorithm is less efficient.Therefore,this paper presents a DEM-assisted oblique aerial image matching method.Firstly,the geometrical deformation is weakened by affine transformation of the oblique image by making full use of the rough Exterior Orientation(EO)elements and DEM data.Secondly,Scale Invariant Feature Transform(SIFT)algorithm is used to match the corrected images to get the corresponding points,and then the false matches in them are eliminated by using the RANdom SAmple Consensus(RANSAC)algorithm.Finally,the homography matrix is used to calculate the corresponding point coordinates on the original image,and the mismatches are eliminated with Fundamental Matrix Estimation method in order to obtain the final corresponding points.Experiments conducted on many sets of oblique images demonstrate that the corresponding points obtained by the proposed algorithm are significantly improved in the computation efficiency,quantity and distribution.
【Fund】: 国家自然科学基金资助项目(41271431 41401536);; 国家科技支撑计划课题(2012BAJ23B03)
【CateGory Index】: P231
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved