Skyline Matching: A robust registration method between Video and GIS - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Skyline Matching: A robust registration method between Video and GIS

Abstract

Camera pose estimation from an image has long been a very active research for Video/GIS registration. Different from traditional methods which are based on direct building feature matching, this paper presents an alternative method which uses an overall Skyline feature to determine the camera's orientation. Through our skyline matching method we find out a way to transform an image/model matching problem into a curve matching problem which significantly reduced the computation complexity and make it a possible solution for real-time applications. 1 Introduction
Fichier principal
Vignette du fichier
Skyline_Matching-Shupeng_ZHU_3U3D_Final.pdf (1.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00768494 , version 1 (21-12-2012)

Identifiers

Cite

Shupeng Zhu, Muriel Pressigout, Myriam Servières, Luce Morin, Guillaume Moreau. Skyline Matching: A robust registration method between Video and GIS. Conference of the European COST Action TU0801 - Semantic Enrichment of 3D City Models for Sustainable Urban Development Location: Grad Sch Architecture, Oct 2012, Nantes, France. pp.1-6, ⟨10.1051/3u3d/201203007⟩. ⟨hal-00768494⟩
282 View
235 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More