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.

@inproceedings{Dohan:2015:LHS,
   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
}