Abstract | ||
---|---|---|
In this paper, a new method for automatic identification of ground control points (GCPs) on optical remote sensing images is presented. An elastic Radial Basis Function (RBF) neural network based model for nonlinear coordinate transformation and image rectification is proposed. The new method can be used to produce dense fields of about thousands of GCPs per image to train highly deformable transformation models. As a result, an accuracy improvement of order of 4 in comparison with the Automated Precise Orthorectification Package (AROP) can be obtained. The proposed method is applied for the Ukrainian remote sensing satellite Sich-2. The obtained average RMSE error by the new method for Sich-2 images is estimated at 17.8 m. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/IGARSS.2014.6946925 | Geoscience and Remote Sensing Symposium |
Keywords | Field | DocType |
artificial satellites,geophysical image processing,mean square error methods,optical images,radial basis function networks,remote sensing,transforms,AROP,GCP,RBF neural network,SICH-2 satellite image orthorectification,Ukrainian remote sensing satellite Sich-2,automated precise orthorectification package,automatic identification method,average RMSE error,elastic radial basis function neural network,ground control point,image rectification,nonlinear coordinate transformation,optical remote sensing imaging,Sich-2,orthorectification,registration | Computer vision,Satellite,Computer science,Remote sensing,Artificial intelligence,Orthophoto | Conference |
ISSN | Citations | PageRank |
2153-6996 | 0 | 0.34 |
References | Authors | |
5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oleksii M. Kravchenko | 1 | 0 | 0.34 |
Mykola Lavrenyuk | 2 | 0 | 0.34 |
Nataliia Kussul | 3 | 191 | 25.01 |