Usability Study of Learning-Based Pose Estimation of Industrial Objects from Synthetic Depth Data - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Usability Study of Learning-Based Pose Estimation of Industrial Objects from Synthetic Depth Data

(1) , (1) , (1)
1
Stefan Thalhammer
  • Function : Author
  • PersonId : 1122689
Timothy Patten
  • Function : Author
  • PersonId : 1122690
Markus Vincze
  • Function : Author
  • PersonId : 1018502

Abstract

For visual assistance systems deployed in an industrial setting, precise object pose estimation is an important task in order to support scene understanding and to enable subsequent grasping and manipulation. Industrial environments are especially challenging since mesh-models are usually available while physical objects are not or are expensive to model. Manufactured objects are often similar in appearance, have limited to no textural cues and exhibit symmetries. Thus, these are especially challenging for recognizers that are meant to provide detection, classification and pose estimation on instance level. A usability study of a recent synthetically trained learning-based recognizer for these particular challenges is conducted. Experiments are performed on the challenging T-LESS dataset due to its relevance for industry.
Embargoed file
Embargoed file
0 10 26
Year Month Jours
Avant la publication

Dates and versions

hal-03520414 , version 1 (11-01-2022)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Stefan Thalhammer, Timothy Patten, Markus Vincze. Usability Study of Learning-Based Pose Estimation of Industrial Objects from Synthetic Depth Data. 9th International Precision Assembly Seminar (IPAS), Dec 2020, Held virtually, Unknown Region. pp.285-296, ⟨10.1007/978-3-030-72632-4_21⟩. ⟨hal-03520414⟩
73 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More