Investigating the Impact of Point Cloud Density on Semantic Segmentation Performance Using Virtual Lidar in Boreal Forest.
Olivier StockerReza Mahmoudi KouhiEric GuilbertAntonio FerrazThierry BadardPublished in: IGARSS (2023)
Keyphrases
- point cloud
- semantic segmentation
- conditional random fields
- structure from motion
- weakly supervised
- superpixels
- scene classification
- point sets
- point cloud data
- laser scanner
- object class
- object categories
- image set
- image processing
- graphical models
- input image
- high quality
- training data
- object classes
- object detection
- pascal voc
- sparse reconstruction
- three dimensional