State-Level Mapping of the Road Transport Network from Aerial Orthophotography: An End-to-End Road Extraction Solution Based on Deep Learning Models Trained for Recognition, Semantic Segmentation and Post-Processing with Conditional Generative Learning.
Calimanut-Ionut CiraMiguel-Ángel Manso-CallejoRamón AlcarriaBorja Bordel SánchezFrancisco Javier González MatesanzPublished in: Remote. Sens. (2023)
Keyphrases
- learning models
- end to end
- post processing
- learning tasks
- learning algorithm
- learning problems
- aerial images
- unsupervised learning
- transport network
- road extraction
- preprocessing
- weakly supervised
- machine learning
- conditional random fields
- semi supervised learning
- active learning
- learning process
- higher order
- data mining
- supervised learning
- prior knowledge
- training set
- feature extraction