Multi-overlapped based global registration of UAV images

Author

Aixia Li ; Zequn Guan ; Haiyan Guan

Author_Institution

Coll. of Surveying & Geo-Inf., Tongji Univ., Shanghai, China

fYear

2012

fDate

16-18 Dec. 2012

Firstpage

105

Lastpage

109

Abstract

A new global registration method based on multi-image matching is proposed for image mosaic. In this study a manifold learning algorithm is first used to obtain multi-images matching results, on which a globally mosaic image coordinate system is then iteratively achieved and utilized to calculate global registration parameters of each image. Testing results indicate that the proposed method has a higher performance than traditional frame-to-frame registration methods in the error accumulation and registration accuracy of mosaic images.

Keywords

image matching; image registration; image segmentation; learning (artificial intelligence); UAV image registration; error accumulation; frame-to-frame registration method; global image registration parameter; globally mosaic image coordinate system; image mosaic; manifold learning algorithm; multiimage matching; multioverlapped based global registration; registration accuracy; unmanned aerial vehicle; Geology; Image edge detection; UAV images; global registration; manifold learning; multi-image matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision in Remote Sensing (CVRS), 2012 International Conference on

Conference_Location

Xiamen

Print_ISBN

978-1-4673-1272-1

Type

conf

DOI

10.1109/CVRS.2012.6421242

Filename

6421242