Remembering Both the Machine and the Crowd When Sampling Points: Active Learning for Semantic Segmentation of ALS Point Clouds.
Michael KölleVolker WalterStefan SchmohlUwe SoergelPublished in: ICPR Workshops (7) (2020)
Keyphrases
- point cloud
- semantic segmentation
- point sets
- active learning
- surface reconstruction
- structure from motion
- conditional random fields
- weakly supervised
- scene classification
- superpixels
- point correspondences
- pairwise
- convex hull
- object categories
- learning algorithm
- feature points
- machine learning
- training set
- video sequences
- object classes
- training data
- multiscale
- training examples
- image classification
- semi supervised