Fast and Lite Point Cloud Semantic Segmentation for Autonomous Driving Utilizing LiDAR Synthetic Training Data.
Jimin JeongHamin SongJaehyun ParkPaulo ResendeBenazouz BradaïKichun JoPublished in: IEEE Access (2022)
Keyphrases
- point cloud
- semantic segmentation
- autonomous driving
- training data
- grand challenge
- conditional random fields
- weakly supervised
- superpixels
- stereo vision
- structure from motion
- decision trees
- scene classification
- point sets
- point cloud data
- data sets
- training set
- object categories
- lidar data
- training examples
- image understanding
- learning algorithm
- supervised learning
- laser scanner
- object classes
- object classification
- machine learning
- three dimensional
- viewpoint
- knn
- object detection
- vision system
- training samples