Contribution to Object Extraction in Cartography : A Novel Deep Learning-Based Solution to Recognise, Segment and Post-Process the Road Transport Network as a Continuous Geospatial Element in High-Resolution Aerial Orthoimagery

Detalles Bibliográficos
Autor: Cira, Calimanut-Ionut|||0000-0002-7713-7238
Tipo de recurso: tesis doctoral
Fecha de publicación:2022
País:España
Institución:Universidad Politécnica de Madrid
Repositorio:Archivo Digital UPM
OAI Identifier:oai:oa.upm.es:70152
Acceso en línea:https://oa.upm.es/70152/
Access Level:acceso abierto
Palabra clave:Aerial Orthoimagery
Artificial Neural Network
Computer Vision
Conditional learning
Convolutional Neural Network
Deep Learning
Ensemble learning
Generative Adversarial Network
Generative Learning
Image Analysis
Image Classification
Image Inpainting
Image Post-processing
Image-to-Image Translation
Remote Sensing
Residual Learning
Road Extraction
Road Recognition
Road Surface Area
Segmentation models
Semantic Segmentation
Supervised Learning
Transfer Learning
Unsupervised Learning
Web-based Segmentation Solution
Descripción
Descripción no disponible.