Dynamic 3D Scene Reconstruction and Enhancement

Abstract : 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.
Type de document :
Pré-publication, Document de travail
2017
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01569314
Contributeur : Cansen Jiang <>
Soumis le : mercredi 26 juillet 2017 - 15:04:17
Dernière modification le : jeudi 27 juillet 2017 - 01:05:53

Fichier

ID230_Camera_Ready.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01569314, version 1

Collections

Citation

Cansen Jiang, Yohan Fougerolle, David Fofi, Cédric Demonceaux. Dynamic 3D Scene Reconstruction and Enhancement. 2017. <hal-01569314>

Partager

Métriques

Consultations de
la notice

79

Téléchargements du document

43