Skip to Main content Skip to Navigation
Master Thesis

Segmentation, classification et modélisation à partir de données issues de capteurs dynamiques

Abstract : Today the need for 3D modeling is more and more important to meet multiple uses such as communication or urban planning. Mobile mapping systems have been developed and used to get wide point cloud to cover a city. These data will allow us to realize most of the time a 3D model of pedestrian type letting appear facade elements (windows, balconies…) and street furniture (candelabra, trees…). At first, classification and segmentation methods will be studied to separate the ground (roads and sidewalks) from facades and elements of street furniture. A process for modeling accurately and lightwise a set of facades and a method of automatic insertion of 3D cells in the software Rhinocéros 3D will be implemented. The purpose of this study was to verify the possibility of obtaining a usable 3D model from data from sensors dynamic.
Document type :
Master Thesis
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://dumas.ccsd.cnrs.fr/dumas-01179612
Contributor : Cnam - Service Commun de la Documentation - Esgt <>
Submitted on : Thursday, July 23, 2015 - 9:01:05 AM
Last modification on : Saturday, February 8, 2020 - 12:02:15 PM
Long-term archiving on: : Saturday, October 24, 2015 - 10:31:20 AM

Identifiers

  • HAL Id : dumas-01179612, version 1

Collections

Citation

Rémi Reboul. Segmentation, classification et modélisation à partir de données issues de capteurs dynamiques. Sciences de l'ingénieur [physics]. 2014. ⟨dumas-01179612⟩

Share

Metrics

Record views

179

Files downloads

2771