A Product Pose Tracking Paradigm Based on Deep Points Detection

The paper at hand presents a novel and versatile method for tracking the pose of varying products during their manufacturing procedure. By using modern Deep Neural Network techniques based on Attention models, the most representative points to track an object can be automatically identified using it...

Full description

Bibliographic Details
Main Authors:	Loukas Bampis, Spyridon G. Mouroutsos, Antonios Gasteratos
Format:	Article
Language:	English
Published:	MDPI AG 2021-05-01
Series:	Machines
Subjects:	deep learning Computer-Aided Manufacturing material processing pose recognition
Online Access:	https://www.mdpi.com/2075-1702/9/6/112

id	doaj-5631072d8e284473b312d2fe0afcc870
record_format	Article
spelling	doaj-5631072d8e284473b312d2fe0afcc8702021-06-01T01:26:15ZengMDPI AGMachines2075-17022021-05-01911211210.3390/machines9060112A Product Pose Tracking Paradigm Based on Deep Points DetectionLoukas Bampis0Spyridon G. Mouroutsos1Antonios Gasteratos2School of Engineering, Democritus University of Thrace, 671 00 Xanthi, GreeceSchool of Engineering, Democritus University of Thrace, 671 00 Xanthi, GreeceSchool of Engineering, Democritus University of Thrace, 671 00 Xanthi, GreeceThe paper at hand presents a novel and versatile method for tracking the pose of varying products during their manufacturing procedure. By using modern Deep Neural Network techniques based on Attention models, the most representative points to track an object can be automatically identified using its drawing. Then, during manufacturing, the body of the product is processed with Aluminum Oxide on those points, which is unobtrusive in the visible spectrum, but easily distinguishable from infrared cameras. Our proposal allows for the inclusion of Artificial Intelligence in Computer-Aided Manufacturing to assist the autonomous control of robotic handlers.https://www.mdpi.com/2075-1702/9/6/112deep learningComputer-Aided Manufacturingmaterial processingpose recognition
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Loukas Bampis Spyridon G. Mouroutsos Antonios Gasteratos
spellingShingle	Loukas Bampis Spyridon G. Mouroutsos Antonios Gasteratos A Product Pose Tracking Paradigm Based on Deep Points Detection Machines deep learning Computer-Aided Manufacturing material processing pose recognition
author_facet	Loukas Bampis Spyridon G. Mouroutsos Antonios Gasteratos
author_sort	Loukas Bampis
title	A Product Pose Tracking Paradigm Based on Deep Points Detection
title_short	A Product Pose Tracking Paradigm Based on Deep Points Detection
title_full	A Product Pose Tracking Paradigm Based on Deep Points Detection
title_fullStr	A Product Pose Tracking Paradigm Based on Deep Points Detection
title_full_unstemmed	A Product Pose Tracking Paradigm Based on Deep Points Detection
title_sort	product pose tracking paradigm based on deep points detection
publisher	MDPI AG
series	Machines
issn	2075-1702
publishDate	2021-05-01
description	The paper at hand presents a novel and versatile method for tracking the pose of varying products during their manufacturing procedure. By using modern Deep Neural Network techniques based on Attention models, the most representative points to track an object can be automatically identified using its drawing. Then, during manufacturing, the body of the product is processed with Aluminum Oxide on those points, which is unobtrusive in the visible spectrum, but easily distinguishable from infrared cameras. Our proposal allows for the inclusion of Artificial Intelligence in Computer-Aided Manufacturing to assist the autonomous control of robotic handlers.
topic	deep learning Computer-Aided Manufacturing material processing pose recognition
url	https://www.mdpi.com/2075-1702/9/6/112
work_keys_str_mv	AT loukasbampis aproductposetrackingparadigmbasedondeeppointsdetection AT spyridongmouroutsos aproductposetrackingparadigmbasedondeeppointsdetection AT antoniosgasteratos aproductposetrackingparadigmbasedondeeppointsdetection AT loukasbampis productposetrackingparadigmbasedondeeppointsdetection AT spyridongmouroutsos productposetrackingparadigmbasedondeeppointsdetection AT antoniosgasteratos productposetrackingparadigmbasedondeeppointsdetection
_version_	1721412332090818560

A Product Pose Tracking Paradigm Based on Deep Points Detection

Similar Items