Spectral characterization and semantic segmentation of complex 3D models in natural environments
Archivos
Fecha
2020-12-10
Autores
Título de la revista
ISSN de la revista
Título del volumen
Editor
Jaén : Universidad de Jaén
Resumen
Esta tesis doctoral presenta sus principales contribuciones en la caracterización de escenarios 3D a partir
de imágenes multiespectrales y la segmentación semántica de nubes de puntos. Como resultado de esta
investigación, se ha desarrollado el software GEU (Geospatial and Envi-ronmental tools of University of
Jaén) que integra el conjunto de métodos desarrollados. Dicha tesis doctoral es presentada por
compendio de publicaciones. La primera parte de la tesis se centra en la fusión de variables espectrales
y morfológicas de estructuras arbóreas que han sido reconstruidas del mundo real. Como áreas de estudio se utilizan una plantación de olivar y una zona forestal. La segunda parte de la tesis se centra en la explotación del conjunto de características intrínsecas a los modelos 3D con el fin de proponer avances
en la segmentación semántica de distintos tipos de materiales y el reconocimiento de patrones
geométricos en viñedos.
This doctoral thesis presents main contributions in the characterization of 3D scenarios from multispectral images and the semantic segmentation of point clouds. As a result of this research, the GEU software (Geospatial and Environmental tools of University of Jaén) has been developed, which integrates the set of methods developed. This doctoral thesis is presented as a compendium of publications. The first part of this dissertation thesis focuses on the fusion of spectral and morphological variables of tree structures which have been reconstructed from the real world. An olive plantation and a forest area are used as study areas. The second part focuses on the analysis of several characteristics intrinsic to 3D models in order to propose advances in the semantic segmentation of different types of natural materials and the recognition of geometric patterns in vineyards.
This doctoral thesis presents main contributions in the characterization of 3D scenarios from multispectral images and the semantic segmentation of point clouds. As a result of this research, the GEU software (Geospatial and Environmental tools of University of Jaén) has been developed, which integrates the set of methods developed. This doctoral thesis is presented as a compendium of publications. The first part of this dissertation thesis focuses on the fusion of spectral and morphological variables of tree structures which have been reconstructed from the real world. An olive plantation and a forest area are used as study areas. The second part focuses on the analysis of several characteristics intrinsic to 3D models in order to propose advances in the semantic segmentation of different types of natural materials and the recognition of geometric patterns in vineyards.
Descripción
Palabras clave
Modelo 3D, viñedos, Imagen multiespectral, fusión de datos, escenarios naturales, olivos, 3D model, vineyards, multispectral imaging, data fusión, natural environments, olive trees
Citación
p.[http://hdl.handle.net/10953/]