Integrating object-based and pixel-based segmentation for building footprint extraction from satellite images
Yazarlar (7)
Dr. Öğr. Üyesi Sohaib K.M. Abujayyab Karabük Üniversitesi, Türkiye
Rania Almajalid
Saudi Electronic University, Suudi Arabistan
Saudi Electronic University, Suudi Arabistan
Raniyah Wazirali
Saudi Electronic University, Suudi Arabistan
Saudi Electronic University, Suudi Arabistan
Rami Ahmad
American University İn The Emirates, Birleşik Arap Emirlikleri
American University İn The Emirates, Birleşik Arap Emirlikleri
Arş. Gör. Enes Taşoğlu Niğde Ömer Halisdemir University, Türkiye
Prof. Dr. İsmail Rakıp KARAŞ Karabük Üniversitesi, Türkiye
Ihab Hijazi
An-Najah National University, Filistin
An-Najah National University, Filistin
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Journal of King Saud University Computer and Information Sciences (Q1) | ||
| Dergi ISSN | 1319-1578 Dergi Bilgileri (2023) | ||
| Dergi Tarandığı Indeksler | SCI-Expanded | ||
| Makale Dili | Türkçe | Basım Tarihi | 12-2023 |
| Cilt / Sayı / Sayfa | 35 / 10 / 101802–0 | DOI | 10.1016/j.jksuci.2023.101802 |
| Makale Linki | http://dx.doi.org/10.1016/j.jksuci.2023.101802 | ||
| UAK Araştırma Alanları |
Bilgi Sistemleri
Görüntü İşleme
|
||
| Özet |
| Accurately delineating building footprints from optical satellite imagery presents a formidable challenge, particularly in urban settings characterized by intricate and diverse structures. Consequently, enhancing the utility of these images for geospatial data updates demands meticulous refinement. Machine learning algorithms have made notable contributions in this context, yet the pursuit of precision remains an ongoing challenge. This paper aims to enhance the accuracy of building footprint extraction through the integration of object-based and pixel-based segmentation techniques. Additionally, it evaluates the performance of machine learning methodologies, specifically LightGBM, XGBoost, and Neural Network (NN) approaches. The model's evaluation employed low spectral resolution optical images, widely accessible and cost-effective for acquisition. The study's outcomes demonstrate a substantial … |
| Anahtar Kelimeler |
| Building footprint extraction | Machine learning | Object-based segmentation | Pixel-based segmentation | Satellite images |
Science Direct
Integrating object-based and pixel-based segmentation for building footprint extraction from satellite images
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Web of Science | 10 |
| Scopus | 15 |
| Google Scholar | 22 |