Fully automatic and robust approach for remote sensing image registration

Authors:
Chi-Farn Chen;Min-Hsin Chen;Hsiang-Tsu Li
Affiliations:
Center for Space and Remote Sensing Research, National Central University, Jhongli, Taiwan;Center for Space and Remote Sensing Research, National Central University, Jhongli, Taiwan;Center for Space and Remote Sensing Research, National Central University, Jhongli, Taiwan
Venue:
CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
Year:
2007

Citing 4
Cited 1

Least-Squares Fitting of Two 3-D Point Sets

IEEE Transactions on Pattern Analysis and Machine Intelligence
Least-Squares Estimation of Transformation Parameters Between Two Point Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
A pyramid approach to subpixel registration based on intensity

IEEE Transactions on Image Processing
A maximum likelihood approach for image registration using control point and intensity

IEEE Transactions on Image Processing

Remote sensing image registration techniques: a survey

ICISP'10 Proceedings of the 4th international conference on Image and signal processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image registration is an important preprocessing procedure for remote sensing image applications, such as geometric correction, change detection, and image fusion. Since it is a time-consuming and labor-intensive task to correctly register the remote sensing image, this paper proposes a fully automatic and robust approach for the remote sensing image registration. First, the image pyramid of working and reference images are constructed for coarse to fine matching processing. Second, the feature points can be automatically extracted from the reference image, and the matching point can be searched on the working image. Third, in order to improve the accuracy of registration, the robust estimation serves as an important tool in preserving the correctly matched points. Three sets of satellite images, which include multi-sensor, multi-temporal and multi-spectrum images, are used to test the proposed approach. Results show that the approach is capable of automatically registering the working image to the reference image with great precision.