Paper
14 May 2014 A sub-pixel registration approach for images from ZY-3 based on the SURF and Harris algorithm
Chong Fan, Juan Zhang
Author Affiliations +
Proceedings Volume 9158, Remote Sensing of the Environment: 18th National Symposium on Remote Sensing of China; 91580E (2014) https://doi.org/10.1117/12.2064161
Event: Remote Sensing of the Environment: 18th National Symposium on Remote Sensing of China, 2012, Wuhan, China
Abstract
In this paper, A new mixed sub-pixel image registration method based on SURF and Harris algorithm is proposed in registering ZY-3 image. The images obtained by ZY-3 Satellite are different in resolution and have local deformation to some extent. The SURF points are invariant on scale and rotating and the Harris algorithm is effective and has high accuracy in the images with same scales. So in the algorithm of this article, the SURF points are firstly extracted and use to make the affine transformation to reconcile the resolution, and then , the Harris points are obtained to built the TIN and make accurate registration in each triangle area. The experimental results prove that the approach is effective for the ZY-3 image registration and the two images are well matched in details. The process of coarse registration based on SURF points can improve the effect of registration. The problem of local deformation is improved and the precision is raised to some extent.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chong Fan and Juan Zhang "A sub-pixel registration approach for images from ZY-3 based on the SURF and Harris algorithm", Proc. SPIE 9158, Remote Sensing of the Environment: 18th National Symposium on Remote Sensing of China, 91580E (14 May 2014); https://doi.org/10.1117/12.2064161
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image registration

Remote sensing

CCD cameras

Image processing

Inspection

Convolution

Gaussian filters

Back to Top