Classification using a three-dimensional sensor in a structured industrial environment - Archive ouverte HAL Access content directly
Journal Articles Journal of Electronic Imaging Year : 2020

Classification using a three-dimensional sensor in a structured industrial environment

Igor Jovančević
Nour Islam Mokhtari
  • Function : Author
Jean-José Orteu

Abstract

Usage of a three-dimensional (3-D) sensor and point clouds provides various benefits over the usage of a traditional camera for industrial inspection. We focus on the development of a classification solution for industrial inspection purposes using point clouds as an input. The developed approach employs deep learning to classify point clouds, acquired via a 3-D sensor, the final goal being to verify the presence of certain industrial elements in the scene. We possess the computer-aided design model of the whole mechanical assembly and an in-house developed localization module provides initial pose estimation from which 3-D point clouds of the elements are inferred. The accuracy of this approach is proved to be acceptable for industrial usage. Robustness of the classification module in relation to the accuracy of the localization algorithm is also estimated.
Fichier principal
Vignette du fichier
JEI_1_2020.pdf (7.5 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02483189 , version 1 (18-02-2020)

Identifiers

Cite

Ivan Mikhailov, Igor Jovančević, Nour Islam Mokhtari, Jean-José Orteu. Classification using a three-dimensional sensor in a structured industrial environment. Journal of Electronic Imaging, 2020, 29 (04), pp.041008. ⟨10.1117/1.JEI.29.4.041008⟩. ⟨hal-02483189⟩
208 View
367 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More