Skip to main content

Learning Hierarchical Semantic Segmentations of LIDAR Data

Author(s): Dohan, David; Matejek, Brian; Funkhouser, Thomas

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1qg08
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDohan, David-
dc.contributor.authorMatejek, Brian-
dc.contributor.authorFunkhouser, Thomas-
dc.date.accessioned2021-10-08T19:46:29Z-
dc.date.available2021-10-08T19:46:29Z-
dc.date.issued2015en_US
dc.identifier.citationDohan, David, Brian Matejek, and Thomas Funkhouser. "Learning Hierarchical Semantic Segmentations of LIDAR Data." In International Conference on 3D Vision (2015): pp. 273-281. doi:10.1109/3DV.2015.38en_US
dc.identifier.urihttps://www.cs.princeton.edu/~funk/3DV15.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1qg08-
dc.description.abstractThis 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 prioritized 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 ~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.en_US
dc.format.extent273 - 281en_US
dc.language.isoen_USen_US
dc.relation.ispartofInternational Conference on 3D Visionen_US
dc.rightsAuthor's manuscripten_US
dc.titleLearning Hierarchical Semantic Segmentations of LIDAR Dataen_US
dc.typeConference Articleen_US
dc.identifier.doi10.1109/3DV.2015.38-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
HierarchicalSemanticSegmentationLidarData.pdf1.35 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.