Communication Dans Un Congrès Année : 2024

Introducing CEA-IMSOLD: an industrial multi-scale object localization dataset

Résumé

We introduce the CEA Industrial Multi-Scale Object Localization Dataset (CEA-IMSOLD), a new BOP format dataset for 6-DoF object localization, crucial for robotics. This dataset aims to evaluate the current localization methods with respect to a new difficulty: large variations in observation distance and, consequently, large variations in image appearance. Compared to the other publicly available datasets, our dataset provides both images with objects small and completely visible in the image, and images where objects are observed close enough so they appear larger than the field of view of the camera. We also propose to consider the observation distance in the evaluation process and introduce new metrics to do so. Finally, our dataset contains a large variety of industrial objects, from small and simple objects such as bolts to sizable and complex ones such as large car parts. We provide baseline results and the dataset is made publicly available to support the community at https://cea-list.github.io/CEA-IMSOLD/.
Fichier principal
Vignette du fichier
IMSOLD_Meden_ICRA24_NoteIEEE.pdf (4.9 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

cea-04683509 , version 1 (02-09-2024)
cea-04683509 , version 2 (18-11-2024)

Identifiants

Citer

Boris Meden, Emmanuel Vega, Fabrice Mayran de Chamisso, Steve Bourgeois. Introducing CEA-IMSOLD: an industrial multi-scale object localization dataset. ICRA 2024 - 2024 IEEE International Conference on Robotics and Automation, May 2024, Yokohama, Japan. pp.17020-17026, ⟨10.1109/ICRA57147.2024.10609999⟩. ⟨cea-04683509v1⟩
89 Consultations
27 Téléchargements

Altmetric

Partager

More