Abstract
Earth Observation (EO) data provides valuable information to localize and monitor deprived areas for the assessment of Sustainable Development Goals (SDGs). We propose a semantic segmentation model that uses a regression output to an important engineered feature as a guide to the weights learning process of the model.
| Original language | English |
|---|---|
| Title of host publication | 2024 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024 |
| Place of Publication | Piscataway, NJ |
| Publisher | IEEE |
| Number of pages | 3 |
| ISBN (Electronic) | 979-8-3503-8967-8 |
| ISBN (Print) | 979-8-3503-8968-5 |
| DOIs | |
| Publication status | Published - 6 Jun 2024 |
| Event | International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024 - Wellington, New Zealand Duration: 8 Apr 2024 → 10 Apr 2024 |
Conference
| Conference | International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024 |
|---|---|
| Abbreviated title | MIGARS 2024 |
| Country/Territory | New Zealand |
| City | Wellington |
| Period | 8/04/24 → 10/04/24 |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 4 Quality Education
Keywords
- 2024 OA procedure
- Deprived areas
- Sentinel-1
- Sentinel-2
- Urban remote sensing
- Deep Learning (DL)
Fingerprint
Dive into the research topics of 'Feature-guided deep learning model for mapping deprived areas'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver