Revue: | Computación y sistemas |
Base de datos: | |
Número de sistema: | 000560630 |
ISSN: | 1405-5546 |
Autores: | Rodríguez Santiago, Armando Levid1 Arias Aguilar, José Aníbal1 Takemura, Hiroshi2 Petrilli Barceló, Alberto Elías2 |
Instituciones: | 1Universidad Tecnológica de la Mixteca, Graduate Studies Division, Oaxaca. México 2Tokyo University of Science, Faculty of Science and Technology, Japón |
Año: | 2021 |
Periodo: | Oct-Dic |
Volumen: | 25 |
Número: | 4 |
Paginación: | 739-749 |
País: | México |
Idioma: | Inglés |
Resumen en inglés | We present a methodology for high-resolution orthomosaic reconstruction using aerial images. Our proposal consists a neural network with two main stages, one to obtain the correspondences necessary to perform a LR-orthomosaic and another one that uses these results to generate an HR- orthomosaic, and a feedback connection. The CNN are based on well known models and are trained to perform image stitching and obtain a high-resolution orthomosaic. The results obtained in this work show that our methodology provides similar results to those obtained by an expert in orthophotography, but in high-resolution. |
Keyword: | Deep learning, CNN, 2D reconstruction, Aerial images, Orthophotography, Photogrammetry |
Texte intégral: | Texto completo (Ver HTML) Texto completo (Ver PDF) |