anomaly_detection_dataset__syria_war
Syria's civil war destruction dataset. It can be use for anomaly detection or semantic segmentation, as well as image classification.
https://github.com/shiman19/anomaly_detection_dataset__syria_war
Science Score: 39.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 6 DOI reference(s) in README -
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.4%) to scientific vocabulary
Keywords
Repository
Syria's civil war destruction dataset. It can be use for anomaly detection or semantic segmentation, as well as image classification.
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
README.md
Syria War Destruction Dataset for Semantic Segmentation
Author: Shima Nabiee
Paper: Hybrid U-Net: Semantic segmentation of high-resolution satellite images to detect war destruction
Journal: Machine Learning with Applications, Volume 9, 2022
Overview
This repository provides a curated dataset of high-resolution satellite imagery from Syria, meticulously annotated to identify war-induced building destruction. The dataset was developed to support research in semantic segmentation, particularly in conflict zones, and was utilized in the study titled Hybrid U-Net: Semantic segmentation of high-resolution satellite images to detect war destruction.
Dataset Structure
Anomaly_Detection_Dataset__Syria_War/
Images/ # High-resolution satellite images (e.g., .jpg, .tif)
Labels/ # Corresponding pixel-wise annotations (e.g., .png)
README.md # Dataset description and usage guidelines
CITATION.cff # Citation information
- Images/: Contains satellite images capturing various regions affected by the Syrian civil war.
- Labels/: Provides binary masks where destroyed buildings are annotated at the pixel level.
Applications
This dataset is suitable for:
- Training and evaluating semantic segmentation models.
- Developing algorithms for automated damage assessment in conflict zones.
- Research in humanitarian aid, urban planning, and post-conflict reconstruction.
Citation
If you utilize this dataset in your research, please cite the following publication:
Nabiee, S., Harding, M., Hersh, J., & Bagherzadeh, N. (2022). Hybrid U-Net: Semantic segmentation of high-resolution satellite images to detect war destruction. Machine Learning with Applications, 9, 100381. https://doi.org/10.1016/j.mlwa.2022.100381
License
This dataset is released under the MIT License. You are free to use, modify, and distribute it, provided that proper attribution is given.
Acknowledgments
We extend our gratitude to the organizations and individuals who provided the satellite imagery and supported the annotation process. Their contributions were invaluable to the development of this dataset.
Related Work
Feel free to integrate this README.md into your repository. If you need further customization or assistance, don't hesitate to ask!
GitHub Events
Total
- Public event: 1
- Push event: 1
Last Year
- Public event: 1
- Push event: 1