Extraction of 3D planar Primitives from Raw Airborne Laser Data: A Normal Driven RANSAC Approach

  • Frédéric Bretar
  • , Michel Roux

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Airborne laser data are nowadays well-known to provide regular and accurate altimetric data. Building reconstruction strategies from traditional stereo images may highly be enhanced us\ng such data together with. The aim of this paper is to propose an efficient algorithm for extracting 3D planar primitives from a laser survey over urban areas, ft is based on a normal driven random sample consensus (ND-RANSAC) which consists of randomly selecting sets of three points within laser points sharing the same orientation of normal vectors. A robust plane is then estimated with laser points that are likely to belong to the real roof facet. The number of draws is managed automatically with a statistical analysis of the distribution of normal vectors within an approximation of the Gaussian sphere of the scene. Promising results are presented with laser data acquired over the city of Amiens, France.

Original languageEnglish
Title of host publicationProceedings of the 9th IAPR Conference on Machine Vision Applications, MVA 2005
PublisherMachine Vision Applications, MVA
Pages452-455
Number of pages4
ISBN (Print)4901122045, 9784901122047
Publication statusPublished - 1 Jan 2005
Externally publishedYes
Event9th IAPR Conference on Machine Vision Applications, MVA 2005 - Tsukuba Science City, Japan
Duration: 16 May 200518 May 2005

Publication series

NameProceedings of the 9th IAPR Conference on Machine Vision Applications, MVA 2005

Conference

Conference9th IAPR Conference on Machine Vision Applications, MVA 2005
Country/TerritoryJapan
CityTsukuba Science City
Period16/05/0518/05/05

Fingerprint

Dive into the research topics of 'Extraction of 3D planar Primitives from Raw Airborne Laser Data: A Normal Driven RANSAC Approach'. Together they form a unique fingerprint.

Cite this