Skip to Main content Skip to Navigation
Journal articles

Model-image registration of a building’s facade based on dense semantic segmentation

Antoine Fond 1, 2 Marie-Odile Berger 1, 3, * Gilles Simon 1, 3
* Corresponding author
1 TANGRAM - Recalage visuel avec des modèles physiquement réalistes
Inria Nancy - Grand Est, UL - Université de Lorraine, LORIA - ALGO - Department of Algorithms, Computation, Image and Geometry, CNRS - Centre National de la Recherche Scientifique
3 MAGRIT - Visual Augmentation of Complex Environments
Inria Nancy - Grand Est, LORIA - ALGO - Department of Algorithms, Computation, Image and Geometry
Abstract : This article presents an efficient approach for accurate registration of a building facade model "dressed" with dense semantic information. Localization sensors such as the GPS as well as vision-based methods are able to provide a camera pose in an efficient and stable way, but at the expense of low accuracy. We propose here to rely on semantic maps to improve the accuracy of a rough camera pose. Simultaneously we aim to iteratively improve the quality of the semantic map through the registration. Registration and semantic segmentation are jointly refined in an Expectation-Maximization framework. We especially introduce a Bayesian model that uses prior semantic segmentation as well as geometric structure of the facade reference modeled by Generalized Gaussian Mixtures. We show the advantages of our method in terms of robustness to clutter and change of illumination on urban images from various databases.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/hal-03204477
Contributor : Marie-Odile Berger <>
Submitted on : Monday, April 26, 2021 - 3:34:54 PM
Last modification on : Saturday, May 1, 2021 - 3:10:24 AM

File

rapport.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Antoine Fond, Marie-Odile Berger, Gilles Simon. Model-image registration of a building’s facade based on dense semantic segmentation. Computer Vision and Image Understanding, Elsevier, 2021, 206, pp.103185. ⟨10.1016/j.cviu.2021.103185⟩. ⟨hal-03204477⟩

Share

Metrics

Record views

55

Files downloads

122