Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.03139 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911566032535552 |
|---|---|
| author | Zhai, Haozhou Gao, Yanzhe Hu, Tianjiang |
| author_facet | Zhai, Haozhou Gao, Yanzhe Hu, Tianjiang |
| contents | Fire scene datasets are crucial for training robust computer vision models, particularly in tasks such as fire early warning and emergency rescue operations. However, among the currently available fire-related data, there is a significant shortage of annotated data specifically targeting building units.To tackle this issue, we introduce an annotated dataset of building units captured by drones, which incorporates multiple enhancement techniques. We construct backgrounds using real multi-story scenes, combine motion blur and brightness adjustment to enhance the authenticity of the captured images, simulate drone shooting conditions under various circumstances, and employ large models to generate fire effects at different locations.The synthetic dataset generated by this method encompasses a wide range of building scenarios, with a total of 1,978 images. This dataset can effectively improve the generalization ability of fire unit detection, providing multi-scenario and scalable data while reducing the risks and costs associated with collecting real fire data. The dataset is available at https://github.com/boilermakerr/FireUnitData. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unit: Building Unit Detection Dataset Zhai, Haozhou Gao, Yanzhe Hu, Tianjiang Computer Vision and Pattern Recognition Fire scene datasets are crucial for training robust computer vision models, particularly in tasks such as fire early warning and emergency rescue operations. However, among the currently available fire-related data, there is a significant shortage of annotated data specifically targeting building units.To tackle this issue, we introduce an annotated dataset of building units captured by drones, which incorporates multiple enhancement techniques. We construct backgrounds using real multi-story scenes, combine motion blur and brightness adjustment to enhance the authenticity of the captured images, simulate drone shooting conditions under various circumstances, and employ large models to generate fire effects at different locations.The synthetic dataset generated by this method encompasses a wide range of building scenarios, with a total of 1,978 images. This dataset can effectively improve the generalization ability of fire unit detection, providing multi-scenario and scalable data while reducing the risks and costs associated with collecting real fire data. The dataset is available at https://github.com/boilermakerr/FireUnitData. |
| title | Unit: Building Unit Detection Dataset |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03139 |