3D point cloud segmentation using GIS

In this paper we propose an approach to perform semantic segmentation of 3D point cloud data by importing the geographic information from a 2D GIS layer (OpenStreetMap). The proposed automatic procedure identifies meaningful units such as buildings and adjusts their locations to achieve best fit between the GIS polygonal perimeters and the point cloud. Our processing pipeline is presented and illustrated by segmenting point cloud data of Trinity College Dublin (Ireland) campus constructed from optical imagery collected by a drone.

[1]  Horst Bischof,et al.  Rapid 3D City Model Approximation from Publicly Available Geographic Data Sources and Georeferenced Aerial Images , 2012 .

[2]  Christoph Strecha,et al.  Classification of Aerial Photogrammetric 3D Point Clouds , 2017, ArXiv.

[3]  Luc Van Gool,et al.  Learning Where to Classify in Multi-view Semantic Segmentation , 2014, ECCV.

[4]  Silvio Savarese,et al.  SEGCloud: Semantic Segmentation of 3D Point Clouds , 2017, 2017 International Conference on 3D Vision (3DV).

[5]  David Moloney,et al.  Trinity College Dublin Drone Survey Dataset , 2017 .

[6]  Luc Van Gool,et al.  Efficient volumetric fusion of airborne and street-side data for urban reconstruction , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[7]  Gabriela Csurka,et al.  What is a good evaluation measure for semantic segmentation? , 2013, BMVC.

[8]  Debra F. Laefer,et al.  Maximizing feature detection in aerial unmanned aerial vehicle datasets , 2017 .

[9]  Richard Szeliski,et al.  Building Rome in a day , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[10]  Mads Haahr.  Creating Location-Based Augmented-Reality Games for Cultural Heritage , 2017, JCSG.

[11]  C. Strecha,et al.  Classification of Aerial Photogrammetric 3D Point Clouds , 2018 .

[12]  Svetlana Lazebnik,et al.  Superparsing , 2010, International Journal of Computer Vision.

[13]  Rozenn Dahyot,et al.  Automatic Discovery and Geotagging of Objects from Street View Imagery , 2017, Remote. Sens..

[14]  Thomas Hofmann,et al.  Learning Aerial Image Segmentation From Online Maps , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Pietro Perona,et al.  From Google Maps to a Fine-Grained Catalog of Street trees , 2019, ArXiv.

[16]  Rozenn Dahyot,et al.  Object Geolocation Using MRF Based Multi-Sensor Fusion , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[17]  Abdullah Bulbul,et al.  Social media based 3D visual popularity , 2017, Comput. Graph..