Share Email Print

Proceedings Paper

Change detection of high resolution satellite imagery considering projection difference
Author(s): Wanshou Jiang; Lihua Xu
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Since image registering is still a difficult problem, the registered images of different time can not match on every pixel, which is usually caused by the differences of object projection from 3D to 2D. The projection differences are usually bigger for prominent objects such as buildings, especially on high resolution imagery, such as IKONOS, QuickBird. The misregistration of images will affect the results of change detection. A method is presented in this paper to lessen the effects of the misregistration. Firstly, the images are registered with a reliable strategy so that the ground can be registered correctly. Then the changes of image are detected with traditional algorithm according to image difference based on an iterative radiometric calibration. At last, region change rate of segmented image are used to improve the change detection results. The experiments show that the false detection of misregistering can be reduced greatly.

Paper Details

Date Published: 2 December 2005
PDF: 6 pages
Proc. SPIE 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications, 60452U (2 December 2005); doi: 10.1117/12.651824
Show Author Affiliations
Wanshou Jiang, Wuhan Univ. (China)
Lihua Xu, Wuhan Univ. (China)

Published in SPIE Proceedings Vol. 6045:
MIPPR 2005: Geospatial Information, Data Mining, and Applications
Jianya Gong; Qing Zhu; Yaolin Liu; Shuliang Wang, Editor(s)

© SPIE. Terms of Use
Back to Top