Paper
2 December 2005 Change detection of high resolution satellite imagery considering projection difference
Wanshou Jiang, Lihua Xu
Author Affiliations +
Proceedings Volume 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications; 60452U (2005) https://doi.org/10.1117/12.651824
Event: MIPPR 2005 SAR and Multispectral Image Processing, 2005, Wuhan, China
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.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wanshou Jiang and Lihua Xu "Change detection of high resolution satellite imagery considering projection difference", Proc. SPIE 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications, 60452U (2 December 2005); https://doi.org/10.1117/12.651824
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Image resolution

Calibration

Image processing

Earth observing sensors

High resolution satellite images

Buildings

Back to Top