Title :
Automatic satellite image registration based on intensity matching
Author :
Jianchao, Yao ; Chern, Chia Tien ; Hwang, Yan Chye ; Adrian, Yap C L
Author_Institution :
Signal Process. Lab., DSO Nat. Labs., Singapore, Singapore
Abstract :
In this paper, a new algorithm for satellite image registration was developed. The main characteristic of the algorithm is to align two images automatically, without requiring either control points or sensor parameters. Thanks to incorporation of a robust estimation mechanism and statistical optimisation technique into a multi-model and multi-resolution framework for intensity matching, the algorithm is able to work with images with large variation in orientation, scaling, illumination and translation. The effectiveness of the algorithm has been verified by an intensive experiment on a great number of real images
Keywords :
estimation theory; geophysical signal processing; image registration; optimisation; remote sensing; automatic satellite image registration; illumination; intensity matching; multi-model framework; multi-resolution framework; orientation; robust estimation mechanism; scaling; statistical optimisation technique; translation; Automatic control; Brightness; Change detection algorithms; Clouds; Image registration; Laboratories; Lighting; Robustness; Satellites; Signal processing algorithms;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-7031-7
DOI :
10.1109/IGARSS.2001.978334
