TU Darmstadt / ULB / TUbiblio

A Survey of 6D Object Detection Based on 3D Models for Industrial Applications

Gorschlüter, Felix ; Rojtberg, Pavel ; Pöllabauer, Thomas (2022)
A Survey of 6D Object Detection Based on 3D Models for Industrial Applications.
In: Journal of Imaging, 2022, 8 (3)
doi: 10.26083/tuprints-00021027
Article, Secondary publication, Publisher's Version

Abstract

Six-dimensional object detection of rigid objects is a problem especially relevant for quality control and robotic manipulation in industrial contexts. This work is a survey of the state of the art of 6D object detection with these use cases in mind, specifically focusing on algorithms trained only with 3D models or renderings thereof. Our first contribution is a listing of requirements typically encountered in industrial applications. The second contribution is a collection of quantitative evaluation results for several different 6D object detection methods trained with synthetic data and the comparison and analysis thereof. We identify the top methods for individual requirements that industrial applications have for object detectors, but find that a lack of comparable data prevents large-scale comparison over multiple aspects.

Item Type: Article
Erschienen: 2022
Creators: Gorschlüter, Felix ; Rojtberg, Pavel ; Pöllabauer, Thomas
Type of entry: Secondary publication
Title: A Survey of 6D Object Detection Based on 3D Models for Industrial Applications
Language: English
Date: 2022
Year of primary publication: 2022
Publisher: MDPI
Journal or Publication Title: Journal of Imaging
Volume of the journal: 8
Issue Number: 3
Collation: 18 Seiten
DOI: 10.26083/tuprints-00021027
URL / URN: https://tuprints.ulb.tu-darmstadt.de/21027
Corresponding Links:
Origin: Secondary publication DeepGreen
Abstract:

Six-dimensional object detection of rigid objects is a problem especially relevant for quality control and robotic manipulation in industrial contexts. This work is a survey of the state of the art of 6D object detection with these use cases in mind, specifically focusing on algorithms trained only with 3D models or renderings thereof. Our first contribution is a listing of requirements typically encountered in industrial applications. The second contribution is a collection of quantitative evaluation results for several different 6D object detection methods trained with synthetic data and the comparison and analysis thereof. We identify the top methods for individual requirements that industrial applications have for object detectors, but find that a lack of comparable data prevents large-scale comparison over multiple aspects.

Uncontrolled Keywords: object detection, pose estimation, machine learning, neural networks, synthetic training, RGBD
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-210272
Classification DDC: 000 Generalities, computers, information > 004 Computer science
600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Fraunhofer IGD
Date Deposited: 11 Apr 2022 11:29
Last Modified: 12 Apr 2022 09:43
PPN:
Corresponding Links:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details