Accéder directement au contenu Accéder directement à la navigation
Nouvelle interface
Article dans une revue

A 3D Segments Based Algorithm for Heterogeneous Data Registration

Abstract : Abstract. Combining image and LiDAR draws increasing interest in surface reconstruction, city and building modeling for constructing 3D virtual reality models because of their complementary nature. However, to gain from this complementarity, these data sources must be precisely registered. In this paper, we propose a new primitive based registration algorithm that takes 3D segments as features. The objective of the proposed algorithm is to register heterogeneous data. The heterogeneity is both in data type (image and LiDAR) and acquisition platform (terrestrial and aerial). Our algorithm starts by extracting 3D segments from LiDAR and image data with state of the art algorithms. Then it clusters the 3D segments of each data according to their directions. The obtained clusters are associated to find possible rotations, then 3D segments from associated clusters are matched in order to find the translation and scale factor minimizing a distance criteria between the two sets of 3D segments. Two optimizers (simulated annealing and RANSAC) are tested to minimize this distance criterion, first on synthetic data, then on real data. The experiments carried out demonstrate the robustness and speed of RANSAC compared to simulated annealing.
Type de document :
Article dans une revue
Liste complète des métadonnées
Contributeur : rahima djahel Connectez-vous pour contacter le contributeur
Soumis le : dimanche 2 octobre 2022 - 19:45:42
Dernière modification le : mercredi 19 octobre 2022 - 09:24:53


Fichiers éditeurs autorisés sur une archive ouverte



Rahima Djahel, Pascal Monasse, Bruno Vallet. A 3D Segments Based Algorithm for Heterogeneous Data Registration. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022, XLIII-B1-2022, pp.129-136. ⟨10.5194/isprs-archives-XLIII-B1-2022-129-2022⟩. ⟨hal-03793989⟩



Consultations de la notice


Téléchargements de fichiers