High Quality Reconstruction of Dynamic Objects using 2D-3D Camera Fusion

Abstract : In this paper, we propose a complete pipeline for high quality reconstruction of dynamic objects using 2D-3D camera setup attached to a moving vehicle. Starting from the segmented motion trajectories of individual objects, we compute their precise motion parameters, register multiple sparse point clouds to increase the density, and develop a smooth and textured surface from the dense (but scattered) point cloud. The success of our method relies on the proposed optimization framework for accurate motion estimation between two sparse point clouds. Our formulation for fusing it closest-point and it consensus based motion estimations, respectively in the absence and presence of motion trajectories, is the key to obtain such accuracy. Several experiments performed on both synthetic and real (KITTI) datasets show that the proposed framework is very robust and accurate.
Type de document :
Pré-publication, Document de travail
This paper has been accepted and will be presented in the IEEE International Conference on Image .. 2017
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01528396
Contributeur : Cansen Jiang <>
Soumis le : vendredi 9 juin 2017 - 18:03:41
Dernière modification le : mercredi 5 juillet 2017 - 12:26:05

Fichier

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

Identifiants

  • HAL Id : hal-01528396, version 2

Collections

Citation

Cansen Jiang, Dennis Christie, Danda Pani Paudel, Cédric Demonceaux. High Quality Reconstruction of Dynamic Objects using 2D-3D Camera Fusion. This paper has been accepted and will be presented in the IEEE International Conference on Image .. 2017. <hal-01528396v2>

Partager

Métriques

Consultations de
la notice

42

Téléchargements du document

49