Please use this identifier to cite or link to this item:
Type of publication: research article
Type of publication (PDB): Straipsnis konferencijos medžiagoje kitose duomenų bazėse / Article in conference proceedings in other databases (P1c)
Field of Science: Informatika / Informatics (N009)
Author(s): Uus, Jonas;Krilavičius, Tomas
Title: Detection of different types of vehicles from aerial imagery
Is part of: CEUR Workshop proceedings [electronic resource]: IVUS 2019, International conference on information technologies, Kaunas, Lithuania, 25 April, 2019. Aachen : CEUR-WS, 2019, Vol. 2470
Extent: p. 80-85
Date: 2019
Keywords: Diverse vehicles;Image obstruction;Dataset
Abstract: Accurate 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 required
Affiliation(s): Baltijos pažangių technologijų institutas, Vilnius
Informatikos fakultetas
Taikomosios informatikos katedra
Vytauto Didžiojo universitetas
Appears in Collections:3. Konferencijų medžiaga / Conference materials
Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml5.5 kBXMLView/Open

MARC21 XML metadata

Show full item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats

CORE Recommender

Page view(s)

checked on Jun 6, 2021


checked on Jun 6, 2021

Google ScholarTM


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