Please use this identifier to cite or link to this item:https://hdl.handle.net/20.500.12259/102060
Full metadata record
DC FieldValueLanguage
dc.contributor.authorUus, Jonas-
dc.contributor.authorKrilavičius, Tomas-
dc.coverage.spatialDE-
dc.date.accessioned2019-12-03T16:49:56Z-
dc.date.available2019-12-03T16:49:56Z-
dc.date.issued2019-
dc.identifier.issn16130073-
dc.identifier.otherVDU02-000062016-
dc.identifier.urihttps://www.vdu.lt/cris/bitstream/20.500.12259/102060/2/ISSN1613-0073_2019_V_2470.PG_80-85.pdf-
dc.identifier.urihttps://hdl.handle.net/20.500.12259/102060-
dc.description.abstractAccurate detection of vehicles in large amounts of imagery is one of the harder objects’ detection tasks as the image resolution can be as high as 16K or sometimes even higher. Difference in vehicles size and their position (direction, they face) is another challenge to overcome to achieve acceptable detection quality. The vehicles can also be partially obstructed, cut off or it may be hard to differentiate between object colour and its foreground. Small size of vehicles in high resolution images complicates the task of accurate detection even more. CNN is one of the most promising methods for image processing, hence, it was decided to use their implementation in YOLO V3. To deal with big high resolution images method for splitting/recombining images and augmenting them was developed. Proposed approach allowed to achieve 81.72% average precision of vehicles detection. Results show practical applicability of such approach for vehicles detection, yet to reach higher accuracy on tractor, off-road and van categories of the vehicles the count in different vehicle categories needs to be balanced, i.e. more examples of the mentioned vehicles are requireden
dc.description.sponsorshipBaltijos pažangių technologijų institutas, Vilnius-
dc.description.sponsorshipInformatikos fakultetas-
dc.description.sponsorshipTaikomosios informatikos katedra-
dc.description.sponsorshipVytauto Didžiojo universitetas-
dc.format.extentp. 80-85-
dc.language.isoen-
dc.relation.ispartofCEUR Workshop proceedings [electronic resource]: IVUS 2019, International conference on information technologies, Kaunas, Lithuania, 25 April, 2019. Aachen : CEUR-WS, 2019, Vol. 2470-
dc.relation.isreferencedbyScopus-
dc.rightshttps://creativecommons.org/licenses/by/4.0/-
dc.subjectDiverse vehiclesen
dc.subjectImage obstructionen
dc.subjectDataseten
dc.subject.classificationStraipsnis konferencijos medžiagoje kitose duomenų bazėse / Article in conference proceedings in other databases (P1c)-
dc.subject.otherInformatika / Informatics (N009)-
dc.titleDetection of different types of vehicles from aerial imageryen
dc.typeresearch article-
dcterms.bibliographicCitation18-
dc.date.updated2019-12-04T10:33Z-
local.object{"source": {"code": "vdu", "handle": "62016"}, "publisher": {"other": ["CEUR-WS"], "list": false}, "db": {"clarivate": false, "scopus": true, "list": true}, "issn": ["1613-0073"], "code": "P1c", "subject": ["N009"], "url": ["https://www.vdu.lt/cris/bitstream/20.500.12259/102060/2/ISSN1613-0073_2019_V_2470.PG_80-85.pdf", "https://hdl.handle.net/20.500.12259/102060"], "country": "DE", "language": "en", "area": "N", "original": true, "pages": 6, "sheets": 0.429, "timestamp": "20191204103327.0", "account": {"year": 2019, "late": false}, "na": 2, "nip": 0, "affiliation": [{"contribution": 0.5, "aip": 1, "country": ["LT"], "rel": "aut", "org": [{"create": true, "contribution": 0.5, "name": "Vytauto Didžiojo universitetas", "id": "111950396", "level": "0", "type": "uni", "research": "1", "status": "1", "unit": {"name": "Informatikos fakultetas", "id": "04", "level": "1", "type": "fak", "research": "1", "status": "1"}}], "id": "3FFC400BF0944C925F0CE6EFF70BB1A8", "lname": "Uus", "fname": "Jonas", "status": "1", "name": "Uus, Jonas"}, {"contribution": 0.5, "aip": 2, "country": ["LT"], "rel": "aut", "org": [{"create": true, "contribution": 0.25, "name": "Vytauto Didžiojo universitetas", "id": "111950396", "level": "0", "type": "uni", "research": "1", "status": "1", "unit": {"name": "Informatikos fakultetas", "id": "04", "level": "1", "type": "fak", "research": "1", "status": "1", "unit": {"name": "Taikomosios informatikos katedra", "id": "0401", "level": "2", "type": "kat", "research": "1", "status": "1"}}}, {"create": false, "contribution": 0.25, "name": "Baltijos pažangių technologijų institutas, Vilnius", "id": "301846141"}], "id": "DD5A5F9F9ADFA0BC37D24E1184ED5391", "lname": "Krilavičius", "fname": "Tomas", "status": "1", "name": "Krilavičius, Tomas"}]}-
local.typeP-
item.fulltextWith Fulltext-
item.grantfulltextopen-
crisitem.author.deptInformatikos fakultetas-
crisitem.author.deptTaikomosios informatikos katedra-
Appears in Collections:3. Konferencijų medžiaga / Conference materials
Universiteto mokslo publikacijos / University Research Publications
Files in This Item:
Show simple item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats


CORE Recommender

Page view(s)

76
checked on Jun 6, 2021

Download(s)

27
checked on Jun 6, 2021

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.