Automatic ground control point extraction for remote sensing image

Kuang Che Lee, Hsuan Ren

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Because of the movement and curvature of the Earth and the rotation of the sensor platform, the remote sensing images always have geographic distortion. In order to correct this distortion and register to reference map, the ground control points (GCP) are needed. They can be used to transform the coordination, so that the image after correction will have the same coordination with the reference. However, the selection of the GCPs is usually done by visual inspection, which is not objective. In this study, we propose a method to automatic select the GCPs. In our proposed method, the Fully Constrained Least Square (FCLS) classifier is adopted for target detection of the images and reference map. Based on the shape and the locations of those targets, they can be paired up automatically and the GCPs can be selected. In the experiment, the FORMOSAT2 images will be used to demonstrate the proposed method and analyze the registration performance.

Original languageEnglish
Title of host publication30th Asian Conference on Remote Sensing 2009, ACRS 2009
Pages1406-1409
Number of pages4
StatePublished - 2009
Event30th Asian Conference on Remote Sensing 2009, ACRS 2009 - Beijing, China
Duration: 18 Oct 200923 Oct 2009

Publication series

Name30th Asian Conference on Remote Sensing 2009, ACRS 2009
Volume3

Conference

Conference30th Asian Conference on Remote Sensing 2009, ACRS 2009
Country/TerritoryChina
CityBeijing
Period18/10/0923/10/09

Keywords

  • Fully Constrained Least Square (FCLS)
  • Geographic registration
  • Ground control point (GCP)

Fingerprint

Dive into the research topics of 'Automatic ground control point extraction for remote sensing image'. Together they form a unique fingerprint.

Cite this