Reducing Annotation Effort: An Innovative Weakly Supervised System for Nationwide Building Extraction Leveraging Open-Source Data
Recent advances in deep learning have improved automated building footprint extraction from satellite imagery, yet nationwide deployment remains challenging due to strong regional variation in building appearance and the high cost of manual annotations required for model generalization. We present a...
محفوظ في:
| المؤلفون الرئيسيون: | , , , |
|---|---|
| التنسيق: | Artigo |
| اللغة: | Inglês |
| منشور في: |
IEEE
2026-01-01
|
| سلاسل: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://ieeexplore.ieee.org/document/11535621/ |
| الوسوم: |
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|