Improvement of automatic building region extraction based on deep neural network segmentation
ABSTRACTThis work seeks to improve the accuracy of building region extraction, in which each pixel in a scenery image is determined to be part of a building or part of the background. Specifically, UNet++ and MANet, which are state-of-the-art deep neural networks (DNNs) for segmentation, were applie...
Kaydedildi:
| Asıl Yazarlar: | , , , |
|---|---|
| Materyal Türü: | Artigo |
| Dil: | Inglês |
| Baskı/Yayın Bilgisi: |
Taylor & Francis Group
2023-10-01
|
| Seri Bilgileri: | Journal of Information and Telecommunication |
| Konular: | |
| Online Erişim: | https://www.tandfonline.com/doi/10.1080/24751839.2023.2197276 |
| Etiketler: |
Etiket eklenmemiş, İlk siz ekleyin!
|