Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/40898
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | michiels | - |
dc.contributor.author | MOONEN, Steven | - |
dc.contributor.author | MICHIELS, Nick | - |
dc.contributor.author | Bey-Temsamani, Abdellatif | - |
dc.contributor.author | VANHERLE, Bram | - |
dc.contributor.author | de Hoog, Joris | - |
dc.contributor.author | Bourgana, Taoufik | - |
dc.date.accessioned | 2023-09-14T14:55:30Z | - |
dc.date.available | 2023-09-14T14:55:30Z | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-09-14T08:50:19Z | - |
dc.identifier.citation | Advances in Artificial Intelligence and Machine Learning, 3 (2) , p. 977 -995 | - |
dc.identifier.uri | http://hdl.handle.net/1942/40898 | - |
dc.description.abstract | Computer vision systems become more wide spread in the manufacturing industry for automating tasks. As these vision systems use more and more machine learning opposed to the classic vision algorithms, streamlining the process of creating the training datasets become more important. Creating large labeled datasets is a tedious and time consuming process that makes it expensive. Especially in a low-volume high-variance manufacturing environment. To reduce the costs of creating training datasets we introduce CAD2Render, a GPU-accelerated synthetic data generator based on the Unity High Definition Render Pipeline * This is an extended and substantially revised version of the paper "CAD2Render: A Modular Toolkit for GPU-Accelerated Moonen, et al. (HDRP). CAD2Render streamlines the process of creating highly customizable synthetic datasets with a modular design for a wide range of variation settings. We validate our toolkit by showcasing the performance of AI vision models trained purely with synthetic data. The performance is tested on object detection and pose estimation problems in a variate of industrial relevant use cases. The code for CAD2Render is available at https: //github.com/EDM-Research/CAD2Render | - |
dc.language.iso | en | - |
dc.subject.other | Synthetic Data | - |
dc.subject.other | Computer vision | - |
dc.subject.other | Machine Learning | - |
dc.subject.other | Graphics | - |
dc.title | CAD2Render: A Synthetic Data Generator for Training Object Detection and Pose Estimation Models in Industrial Environments | - |
dc.type | Journal Contribution | - |
dc.identifier.epage | 995 | - |
dc.identifier.issue | 2 | - |
dc.identifier.spage | 977 | - |
dc.identifier.volume | 3 | - |
local.bibliographicCitation.jcat | A2 | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
dc.identifier.doi | 10.54364/AAIML.2023.1158 | - |
local.provider.type | - | |
local.uhasselt.international | no | - |
item.fullcitation | MOONEN, Steven; MICHIELS, Nick; Bey-Temsamani, Abdellatif; VANHERLE, Bram; de Hoog, Joris & Bourgana, Taoufik (2023) CAD2Render: A Synthetic Data Generator for Training Object Detection and Pose Estimation Models in Industrial Environments. In: Advances in Artificial Intelligence and Machine Learning, 3 (2) , p. 977 -995. | - |
item.contributor | MOONEN, Steven | - |
item.contributor | MICHIELS, Nick | - |
item.contributor | Bey-Temsamani, Abdellatif | - |
item.contributor | VANHERLE, Bram | - |
item.contributor | de Hoog, Joris | - |
item.contributor | Bourgana, Taoufik | - |
item.accessRights | Open Access | - |
item.fulltext | With Fulltext | - |
crisitem.journal.eissn | 2582-9793 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
CAD2Render.pdf | Published version | 13.44 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.