Semantic segmentation of very-high spatial resolution satellite images: A comparative analysis of 3D-CNN and traditional machine learning algorithms for automatic vineyard detection

Basit Öğe Kaydı
dc.contributor.authorAkar, Özlem
dc.contributor.authorSaralioğlu, Ekrem
dc.contributor.authorGüngör, Oğuz
dc.contributor.authorBayata, Halim Ferit
dc.date.accessioned2024-11-18T06:37:31Z
dc.date.available2024-11-18T06:37:31Z
dc.date.issued2024
dc.departmentAÇÜ, Mühendislik Fakültesi, Harita Mühendisliği Bölümüen_US
dc.description.abstractThe Erzincan (Cimin) grape, which is an endemic product, plays a significant role in the economy of both the region it is cultivated in and the overall country. Therefore, it is crucial to closely monitor and promote this product. The objective of this study was to analyze the spatial distribution of vineyards by utilizing advanced machine learning and deep learning algorithms to classify high-resolution satellite images. A deep learning model based on a 3D Convolutional Neural Network (CNN) was developed for vineyard classification. The proposed model was compared with traditional machine learning algorithms, specifically Support Vector Machine (SVM), Random Forest (RF), and Rotation Forest (ROTF). The accuracy of the classifications was assessed through error matrices, kappa analysis, and McNemar tests. The best overall classification accuracies and kappa values were achieved by the 3D CNN and RF methods, with scores of 86.47% (0.8308) and 70.53% (0.6279) respectively. Notably, when Gabor texture features were incorporated, the accuracy of the RF method increased to 75.94% (0.6364). Nevertheless, the 3D CNN classifier outperformed all others, yielding the highest classification accuracy with an 11% advantage (86.47%). The statistical analysis using McNemar's test confirmed that the ?2 values for all classification outcomes exceeded 3.84 at the 95% confidence interval, indicating a significant enhancement in classification accuracy provided by the 3D CNN classifier. Additionally, the 3D CNN method demonstrated successful classification performance, as evidenced by the minimum-maximum F1-score (0.79-0.97), specificity (0.95-0.99), and accuracy (0.91-0.99) values.
dc.identifier.doi10.26833/ijeg.1252298
dc.identifier.endpage24en_US
dc.identifier.issue1en_US
dc.identifier.scopusqualityQ2
dc.identifier.startpage12en_US
dc.identifier.urihttp://dx.doi.org/10.26833/ijeg.1252298
dc.identifier.urihttps://hdl.handle.net/11494/4960
dc.identifier.volume9en_US
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakTR-Dizin
dc.institutionauthorSaralioğlu, Ekrem
dc.language.isoenen_US
dc.publisherMersin Üniversitesien_US
dc.relation.ispartofInternational Journal of Engineering and Geosciences
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectMachine Learningen_US
dc.subjectDeep Learningen_US
dc.subjectRandom Foresten_US
dc.subjectGaboren_US
dc.subjectImage Classificationen_US
dc.titleSemantic segmentation of very-high spatial resolution satellite images: A comparative analysis of 3D-CNN and traditional machine learning algorithms for automatic vineyard detectionen_US
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
ozlem.akar-ekrem.saralioglu-oguz.gungor-halim.bayata.pdf
Boyut:
767.4 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu
Harita Mühendisliği Bölümü Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu