Skip navigation
Please use this identifier to cite or link to this item: https://libeldoc.bsuir.by/handle/123456789/54372
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBin Lei-
dc.contributor.authorWei Wan-
dc.contributor.authorNedzved, A.-
dc.contributor.authorNedzved, A.-
dc.contributor.authorBelotserkovsky, A.-
dc.coverage.spatialМинскen_US
dc.date.accessioned2024-02-26T11:41:46Z-
dc.date.available2024-02-26T11:41:46Z-
dc.date.issued2023-
dc.identifier.citationConstruction of a semi-automatic contour of areal objects on hyperspectral satellite images / Bin Lei [et al.] // Pattern Recognition and Information Processing (PRIP'2023) = Распознавание образов и обработка информации (2023) : Proceedings of the 16th International Conference, October 17–19, 2023, Minsk, Belarus / United Institute of Informatics Problems of the National Academy of Sciences of Belarus. – Minsk, 2023. – P. 135–138.en_US
dc.identifier.urihttps://libeldoc.bsuir.by/handle/123456789/54372-
dc.description.abstractIn this article, we formalize the problem of constructing a semi-automatic contour of areal objects on satellite hyperspectral images, and present a solution algorithm using PCA and Dijkstra's algorithm. The contour is considered as the boundary of the object, which can be used for its segmentation and classification. The semi-automatic contour assumes reference points set by the operator. The formalization of the algorithm has been completed.en_US
dc.language.isoenen_US
dc.publisherBSUen_US
dc.subjectматериалы конференцийen_US
dc.subjecthyperspectrumen_US
dc.subjectmultispectrumen_US
dc.subjectcontouren_US
dc.subjectfeature spaceen_US
dc.titleConstruction of a semi-automatic contour of areal objects on hyperspectral satellite imagesen_US
dc.typeArticleen_US
Appears in Collections:Pattern Recognition and Information Processing (PRIP'2023) = Распознавание образов и обработка информации (2023)

Files in This Item:
File Description SizeFormat 
Bin_Lei_Construction.pdf639.71 kBAdobe PDFView/Open
Show simple item record Google Scholar

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