PrincetonComputer SciencePIXL GroupPublications → [Dohan et al. 2015] Local Access
Learning Hierarchical Semantic Segmentations of LIDAR Data

International Conference on 3D Vision (3DV), October 2015

David Dohan, Brian Matejek, Thomas Funkhouser
Example Ground Truth of LIDAR Scan from Google Street View

This paper investigates a method for semantic segmentation of small objects in terrestrial LIDAR scans in urban environments. The core research contribution is a hierarchical segmentation algorithm where potential merges between segments are ordered by a learned affinity function and constrained to occur only if they achieve a significantly high object classification probability. This approach provides a way to integrate a learned shape-prior (the object classifier) into a search for the best semantic segmentation in a fast and practical algorithm. Experiments with LIDAR scans collected by Google Street View cars throughout $sim$100 city blocks of New York City show that the algorithm provides better segmentations and classifications than simple alternatives for cars, vans, traffic lights, and street lights.
Supplemental Material

David Dohan, Brian Matejek, and Thomas Funkhouser.
"Learning Hierarchical Semantic Segmentations of LIDAR Data."
International Conference on 3D Vision (3DV), October 2015.


   author = "David Dohan and Brian Matejek and Thomas Funkhouser",
   title = "Learning Hierarchical Semantic Segmentations of {LIDAR} Data",
   booktitle = "International Conference on 3D Vision (3DV)",
   year = "2015",
   month = oct