Real-time 2D–3D door detection and state classification on a low-power device

Ramôa, João Gaspar; Lopes, Vasco; Alexandre, Luís; Mogo, Sandra

Publication

Real-time 2D–3D door detection and state classification on a low-power device

2021Journal article

dc.contributor.author	Ramôa, João Gaspar
dc.contributor.author	Lopes, Vasco
dc.contributor.author	Alexandre, Luís
dc.contributor.author	Mogo, Sandra
dc.date.accessioned	2023-01-10T09:44:50Z
dc.date.available	2023-01-10T09:44:50Z
dc.date.issued	2021
dc.description.abstract	In this paper, we propose three methods for door state classifcation with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work ofine, in low-powered computers as the Jetson Nano, in real-time with the ability to diferentiate between open, closed and semi-open doors. We use the 3D object classifcation, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classifcation networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classifcation algorithm running in real-time on a low-power device.	pt_PT
dc.description.version	info:eu-repo/semantics/publishedVersion	pt_PT
dc.identifier.doi	10.1007/s42452-021-04588-3	pt_PT
dc.identifier.uri	http://hdl.handle.net/10400.6/12633
dc.language.iso	eng	pt_PT
dc.peerreviewed	yes	pt_PT
dc.relation	NOVA Laboratory for Computer Science and Informatics
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/	pt_PT
dc.subject	Door detection	pt_PT
dc.subject	Door state classifcation	pt_PT
dc.subject	Door segmentation	pt_PT
dc.subject	Jetson nano	pt_PT
dc.subject	2D–3D Door dataset	pt_PT
dc.subject	Real-Time	pt_PT
dc.title	Real-time 2D–3D door detection and state classification on a low-power device	pt_PT
dc.type	journal article
dspace.entity.type	Publication
oaire.awardTitle	NOVA Laboratory for Computer Science and Informatics
oaire.awardURI	info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04516%2F2020/PT
oaire.citation.issue	5	pt_PT
oaire.citation.title	SN Applied Sciences	pt_PT
oaire.citation.volume	3	pt_PT
oaire.fundingStream	6817 - DCRRNI ID
person.familyName	Ramôa
person.familyName	FERRINHO LOPES
person.familyName	Alexandre
person.familyName	Mogo
person.givenName	Gaspar
person.givenName	VASCO
person.givenName	Luís
person.givenName	Sandra
person.identifier	2445498
person.identifier	bvYBcRkAAAAJ
person.identifier	340036
person.identifier.ciencia-id	2516-C038-0DC1
person.identifier.ciencia-id	2014-0F06-A3E3
person.identifier.ciencia-id	1717-63EA-3853
person.identifier.orcid	0000-0002-8884-0922
person.identifier.orcid	0000-0002-5577-1094
person.identifier.orcid	0000-0002-5133-5025
person.identifier.orcid	0000-0002-1423-2668
person.identifier.rid	E-8770-2013
person.identifier.scopus-author-id	8847713100
person.identifier.scopus-author-id	6508333851
project.funder.identifier	http://doi.org/10.13039/501100001871
project.funder.name	Fundação para a Ciência e a Tecnologia
rcaap.rights	openAccess	pt_PT
rcaap.type	article	pt_PT
relation.isAuthorOfPublication	68af7f0f-e088-41c3-95a6-f997b883e1f9
relation.isAuthorOfPublication	a8a77d1f-0219-4739-a346-1b1ae649a47d
relation.isAuthorOfPublication	131ec6eb-b61a-4f27-953f-12e948a43a96
relation.isAuthorOfPublication	4c37dfc5-2e33-49f8-b105-5421875a536d
relation.isAuthorOfPublication.latestForDiscovery	131ec6eb-b61a-4f27-953f-12e948a43a96
relation.isProjectOfPublication	ccebc324-b0d7-400f-9c95-b6a8ac0149be
relation.isProjectOfPublication.latestForDiscovery	ccebc324-b0d7-400f-9c95-b6a8ac0149be