Proposed a Method for Orthophoto Generation with Neural Networks Using Ikonose Geo...

Proposed a Method for Orthophoto Generation with Neural Networks Using Ikonose Geo Images

SHARE

Abstract


Proposed a Method for Orthophoto Generation with Neural Networks Using Ikonose Geo Images

Jalal Amini
Department of Geomatics Engineering, Faculty of Engineering
University of Tehran
Tehran, Iran
Email: [email protected]

Mahdi Saati
Department of Geomatics Engineering, Faculty of Engineering, University of Tehran

Abstract
Generation of orthophoto from high resolution satellite images is an important problem for various remote sensing and phorogrammetric applications. In this paper, we proposed a method that used artificial neural networks for orthophoto generation of Ikonos Geo images. The proposed method consists of two steps. In the first step, the learning data is determined and in the second step the network is designed and using for orthophoto generation. We used bilinear interpolation method for grey level resampling and DLT model for determination of learning data set in the first step. A multi layer perceptron with back propagation learning method is used for orthophoto generation in this paper. The method of this paper is tested over an Ikonos Geo image from an area in Iran.