Skyline variations allow estimating distance to trees on landscape photos using semantic segmentation.
Laura Martinez-SanchezDaniele BorioRaphaël d'AndrimontMarijn Van der VeldePublished in: Ecol. Informatics (2022)
Keyphrases
- semantic segmentation
- street scenes
- label transfer
- conditional random fields
- superpixels
- weakly supervised
- scene classification
- decision trees
- pascal voc
- image understanding
- object classes
- object categories
- object class
- object detection
- segmentation algorithm
- pixel level
- multi class
- knn
- probabilistic model
- active learning
- multiscale
- training data