LIDAR-AIDED TOTAL VARIATION REGULARIZED NONNEGATIVE TENSOR FACTORIZATION FOR HYPERSPECTRAL UNMIXING

Basit Öğe Kaydı
dc.authorscopusid57222722659
dc.authorscopusid57215322367
dc.authorscopusid57195216406
dc.contributor.authorKaya, Atakan
dc.contributor.authorAtas, Kubilay
dc.contributor.authorKahraman, Sevcan
dc.date.accessioned2024-09-11T19:59:01Z
dc.date.available2024-09-11T19:59:01Z
dc.date.issued2021
dc.departmentİstanbul Gelişim Üniversitesien_US
dc.descriptionThe Institute of Electrical and Electronics Engineers Geoscience and Remote Sensing Society (GRSS)en_US
dc.description2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 -- 12 July 2021 through 16 July 2021 -- Brussels -- 176845en_US
dc.description.abstractHyperspectral unmixing (HU) is an important research field in hyperspectral image processing. In recent years, Nonnegative Tensor Factorization (NTF)-based methods have gained great importance in remote sensing imagery, especially hyperspectral unmixing, regardless of any information loss. Nevertheless, NTF has some disadvantages, such as signal-to-noise ratio (SNR) and noncovexity conditions. Mentioned problem can be solved by introducing some spatial regularizations. On the other hand, LiDAR data provides Digital Surface Model (DSM) information gives accurate elevation information about the observed scene. Moreover, total variation (TV)-based regularization provides piecewise smoothness and it preserve edge structure information in the abundance maps. However, this property could be inappropriate for pixels located in edges. LiDAR-DSM alleviates this problem by contributing neighboring objects pixels differently. In this paper, we proposed a simple yet efficient HU framework that incorporates LiDAR data with TV regularized matrix-vector NTF method (LiMVNTF-TV). Experimental studies are carried out on simulation data sets and demonstrate that the proposed framework can provide better abundance estimation maps. © 2021 IEEE.en_US
dc.description.sponsorshipIstanbul Gelisim University Scientific Research Projects Application and Research Center, (BP-070220-SK)en_US
dc.description.sponsorshipThe authors would like to thank F. Xiong, Y. Qian, J. Zhou and Y. Y. Tang for providing the code of [8]. This study has been funded by Istanbul Gelisim University Scientific Research Projects Application and Research Center. Project number: BP-070220-SK.en_US
dc.identifier.doi10.1109/IGARSS47720.2021.9553137
dc.identifier.endpage5066en_US
dc.identifier.isbn978-166540369-6en_US
dc.identifier.scopus2-s2.0-85126053787en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage5063en_US
dc.identifier.urihttps://doi.org/10.1109/IGARSS47720.2021.9553137
dc.identifier.urihttps://hdl.handle.net/11363/8614
dc.identifier.volume2021-Julyen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofInternational Geoscience and Remote Sensing Symposium (IGARSS)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240903_Gen_US
dc.subjectADMM; Data fusion; Hyperspectral (HS) image; Light detection; NTF; Ranging (LiDAR); Spectral unmixing; Total variationen_US
dc.titleLIDAR-AIDED TOTAL VARIATION REGULARIZED NONNEGATIVE TENSOR FACTORIZATION FOR HYPERSPECTRAL UNMIXINGen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu