Dynamic 3D Scene Reconstruction and Enhancement - Université de Bourgogne Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Dynamic 3D Scene Reconstruction and Enhancement

Résumé

In this paper, we present a 3D reconstruction and enhancement approach for high quality dynamic city scene reconstructions. We first detect and segment the moving objects using 3D Motion Segmenta-tion approach by exploiting the feature trajectories' behaviours. Getting the segmentations of both the dynamic scene parts and the static scene parts, we propose an efficient point cloud registration approach which takes the advantages of 3-point RANSAC and Iterative Closest Points algorithms to produce precise point cloud alignment. Furthermore, we proposed a point cloud smoothing and texture mapping framework to enhance the results of reconstructions for both the static and the dynamic scene parts. The proposed algorithms are evaluated using the real-world challenging KITTI dataset with very satisfactory results.
Fichier principal
Vignette du fichier
ID230_Camera_Ready.pdf (2.93 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01569314 , version 1 (26-07-2017)

Identifiants

  • HAL Id : hal-01569314 , version 1

Citer

Cansen Jiang, Yohan Fougerolle, David Fofi, Cédric Demonceaux. Dynamic 3D Scene Reconstruction and Enhancement. IAPR 19th International Conference in Image Analysis and Processing (ICIAP17), Sep 2017, Catania, Italy. ⟨hal-01569314⟩
292 Consultations
634 Téléchargements

Partager

Gmail Facebook X LinkedIn More