VEPL-Net: A Deep Learning Ensemble for Automatic Segmentation of Vegetation Encroachment in Power Line Corridors Using UAV Imagery.
Mateo Cano-SolisJohn R. BallesterosGermán Sánchez TorresPublished in: ISPRS Int. J. Geo Inf. (2023)
Keyphrases
- power line
- automatic segmentation
- deep learning
- tree crown
- manual segmentation
- automatically segmenting
- low voltage
- segmentation algorithm
- unsupervised learning
- semi automatic segmentation
- machine learning
- unsupervised feature learning
- image data
- high resolution
- training set
- computer vision
- weakly supervised
- ecg signals
- training data
- feature selection
- learning algorithm
- mental models
- natural images
- input image
- image processing