Generation of Orthoimage from High-Resolution DEM and High-Resolution Image

Generating an orthoimage from high-resolution satellite images is an important undertaking forvarious remote sensing and photogrammetric applications. in this paper, a method is proposedthat uses artificial neural networks (ann) to generate orthoimage ikonos geo images. fororthoimage generation, a digital elevation model (oem) with a cell size of 4 m and rms errorof 0.24 m is constructed with neural networks, based on a quad tree (qt) structure. in orderto determine object-to-image relationships, rational function models, polynomials and neuralnetworks with back propagation learning algorithms were used. ground control points (gcps)and check points were taken from topographic maps of 1:2000, with a contour interval of 2.5 m,to evaluate the accuracy of oem and object-to-image transformations. the method describedin this paper is tested with an ikonos geo image from a region of bilesavar, iran.