---
license: cc-by-nc-sa-4.0
task_categories:
  - visual-question-answering
  - image-classification
  - image-segmentation
language:
  - en
  - zh
  - ja
tags:
  - disaster-recognition
  - satellite-imagery
  - remote-sensing
  - vision-language
  - multi-modal
  - xview2
size_categories:
  - 10K<n<100K
pretty_name: xView2 Multi-Language Disaster Recognition Dataset
---

# xView2 Multi-Language Disaster Recognition Dataset

This dataset is derived from the xBD (xView2) Building Damage Assessment Dataset and has been reformatted for Vision-Language Model (VLM) training with multi-language support.

## 📊 Dataset Overview

This dataset contains satellite imagery paired with multi-language conversational annotations for disaster recognition tasks. It supports three languages: **English**, **Chinese (中文)**, and **Japanese (日本語)**.

### Dataset Splits

- **Training Set (tier3)**: 9,168 image pairs → 55,008 conversations
- **Test Set**: 933 image pairs → 5,598 conversations
- **Total**: 10,101 image pairs → 60,606 multi-language conversations

Each image pair consists of:
- Pre-disaster satellite image
- Post-disaster satellite image
- Corresponding segmentation masks
- Building damage labels
- Metadata (capture date, sun position, sensor info)

## 🗂️ Dataset Structure

### Downloadable Files (Available on HuggingFace)

The dataset is provided as compressed archives to facilitate downloading:

```
xview2/
├── xview2_train.tar.gz             # Training split (8.04 GB compressed)
├── xview2_tier3.tar.gz             # Additional training data (17.79 GB compressed)
├── xview2_test.tar.gz              # Test split (2.67 GB compressed)
├── xview2_train_tier3.json         # Training metadata
├── xview2_test.json                # Test metadata
├── xview2_train_tier3_sharegpt.json # Training conversations (ShareGPT format)
├── xview2_test_sharegpt.json       # Test conversations (ShareGPT format)
├── verify_dataset.py               # Dataset integrity verification script
├── README.md                       # This file
└── samples/images/                 # Sample images for preview
    ├── guatemala-volcano_00000000_pre_disaster.png
    ├── guatemala-volcano_00000000_post_disaster.png
    ├── hurricane-florence_00000004_post_disaster.png
    └── santa-rosa-wildfire_00000000_post_disaster.png
```

### After Extraction

Once you extract the compressed archives, the structure will be:

```
xview2/
├── train/                          # Training split (extracted from xview2_train.tar.gz)
│   ├── images/                     # Satellite images (pre/post disaster)
│   ├── masks/                      # Segmentation masks
│   ├── color_masks/                # Visualization masks
│   └── labels/                     # Building annotations (JSON)
├── tier3/                          # Additional training data (extracted from xview2_tier3.tar.gz)
│   ├── images/
│   ├── masks/
│   ├── color_masks/
│   └── labels/
├── test/                           # Test split (extracted from xview2_test.tar.gz)
│   ├── images/
│   ├── masks/
│   ├── color_masks/
│   └── labels/
└── ... (metadata and conversation files)
```

## 🌍 Disaster Types

The dataset covers 6 types of natural disasters:

| Type | English | 中文 | 日本語 | Examples |
|------|---------|------|--------|----------|
| volcano | Volcano | 火山 | 火山 | Guatemala volcano |
| flooding | Flooding | 洪水 | 洪水 | Hurricane Florence, Hurricane Harvey |
| wind | Wind damage | 风灾 | 風災 | Hurricane Matthew, Hurricane Michael |
| earthquake | Earthquake | 地震 | 地震 | Mexico earthquake |
| tsunami | Tsunami | 海啸 | 津波 | Palu tsunami |
| fire | Fire | 火灾 | 火災 | Santa Rosa wildfire, SoCal fire |

## 🖼️ Sample Images

The `samples/images/` directory contains example images for preview:

- **Guatemala Volcano (Pre-disaster)**: `guatemala-volcano_00000000_pre_disaster.png`
- **Guatemala Volcano (Post-disaster)**: `guatemala-volcano_00000000_post_disaster.png`
- **Hurricane Florence (Post-disaster)**: `hurricane-florence_00000004_post_disaster.png`
- **Santa Rosa Wildfire (Post-disaster)**: `santa-rosa-wildfire_00000000_post_disaster.png`

## 💬 Conversation Format

The dataset uses ShareGPT format with two-turn conversations:

### Real Example: Guatemala Volcano (Post-disaster - Chinese)

**Image**: `train/images/guatemala-volcano_00000000_post_disaster.png` (see sample above)

```json
{
  "id": "xview2_train_000000_post_zh",
  "images": ["data/xview2/train/images/guatemala-volcano_00000000_post_disaster.png"],
  "messages": [
    {
      "from": "human",
      "value": "<image>\n这张图片中发生了灾害吗？"
    },
    {
      "from": "gpt",
      "value": "是的，这张图片中发生了灾害。这是灾后图像。"
    },
    {
      "from": "human",
      "value": "这张图片中发生了什么类型的灾害？"
    },
    {
      "from": "gpt",
      "value": "这张图片中发生了火山灾害。"
    }
  ]
}
```

### Real Example: Guatemala Volcano (Pre-disaster - English)

**Image**: `train/images/guatemala-volcano_00000000_pre_disaster.png` (see sample above)

```json
{
  "id": "xview2_train_000000_pre_en",
  "images": ["data/xview2/train/images/guatemala-volcano_00000000_pre_disaster.png"],
  "messages": [
    {
      "from": "human",
      "value": "<image>\nHas a disaster occurred in this image?"
    },
    {
      "from": "gpt",
      "value": "No, no disaster has occurred in this image. This is a pre-disaster image."
    },
    {
      "from": "human",
      "value": "What type of disaster occurred in this image?"
    },
    {
      "from": "gpt",
      "value": "No disaster has occurred. This image was taken before the disaster."
    }
  ]
}
```

### Real Example: Guatemala Volcano (Post-disaster - Japanese)

```json
{
  "id": "xview2_train_000000_post_ja",
  "images": ["data/xview2/train/images/guatemala-volcano_00000000_post_disaster.png"],
  "messages": [
    {
      "from": "human",
      "value": "<image>\nこの画像では災害が発生していますか？"
    },
    {
      "from": "gpt",
      "value": "はい、この画像では災害が発生しています。これは災害後の画像です。"
    },
    {
      "from": "human",
      "value": "この画像ではどのような種類の災害が発生しましたか？"
    },
    {
      "from": "gpt",
      "value": "この画像では火山災害が発生しました。"
    }
  ]
}
```

## 📚 Original Dataset Citation

This dataset is based on the **xBD (xView2) Dataset**:

```bibtex
@InProceedings{Gupta_2019_CVPR_Workshops,
  author = {Gupta, Ritwik and Goodman, Bryce and Patel, Nirav and Hosfelt, Ricky and Sajeev, Sandra and Heim, Eric and Doshi, Jigar and Lucas, Keane and Choset, Howie and Gaston, Matthew},
  title = {Creating xBD: A Dataset for Assessing Building Damage from Satellite Imagery},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month = {June},
  year = {2019},
  pages = {10-17}
}
```

**Paper Abstract**: xBD is a large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research. The dataset provides pre- and post-event multi-band satellite imagery from a variety of disaster events with building polygons, classification labels for damage types, ordinal labels of damage level, and corresponding satellite metadata. xBD contains ~700,000 building annotations across over 5,000 km² of imagery from 15 countries.

## 🔗 Data Source

- **Original Dataset**: [https://xview2.org/dataset](https://xview2.org/dataset)
- **License**: [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/)

## 📋 License

This derivative dataset follows the original license:

**CC BY-NC-SA 4.0** - You are free to:
- **Share** — copy and redistribute the material in any medium or format
- **Adapt** — remix, transform, and build upon the material

Under the following terms:
- **Attribution** — You must give appropriate credit, provide a link to the license, and indicate if changes were made
- **NonCommercial** — You may not use the material for commercial purposes
- **ShareAlike** — If you remix, transform, or build upon the material, you must distribute your contributions under the same license

## 🎯 Use Cases

This dataset is suitable for:

1. **Vision-Language Model Training**: Multi-modal models that understand disaster imagery
2. **Multi-language AI Systems**: Models that can communicate about disasters in multiple languages
3. **Disaster Assessment**: Automated systems for rapid disaster type identification
4. **Change Detection**: Pre/post disaster image comparison
5. **Humanitarian AI**: Applications for disaster response and recovery

## 📦 How to Use

### Step 1: Download and Extract

```bash
# Download from HuggingFace, then extract
tar -xzf xview2_train.tar.gz
tar -xzf xview2_tier3.tar.gz
tar -xzf xview2_test.tar.gz
```

### Step 2: Verify Dataset Integrity

```bash
python verify_dataset.py
```

**Expected Output**: 
```
Verifying dataset integrity... 
✅ Dataset is ready
```

For detailed verification report:
```bash
python verify_dataset.py --verbose
```

### Step 3: Load and Use

```python
import json
from PIL import Image

# Load conversations
with open('xview2_train_tier3_sharegpt.json', 'r', encoding='utf-8') as f:
    conversations = json.load(f)

# Get first conversation
conv = conversations[0]

# Load image
image = Image.open(conv['images'][0])

# Access conversation
print(conv['messages'][0]['value'])  # Question 1
print(conv['messages'][1]['value'])  # Answer 1
```

## 📚 Citation

If you use this dataset in your research, please cite:

```bibtex
@misc{xview2_multi_language_2024,
  title = {xView2 Multi-Language Disaster Recognition Dataset},
  author = {WayBob},
  year = {2025},
  howpublished = {\url{https://huggingface.co/datasets/WayBob/Disaster_Recognition_RemoteSense_EN_CN_JA}},
  note = {A multi-language Vision-Language Model training dataset derived from xBD (xView2)}
}
```

And please also cite the original xBD dataset:

```bibtex
@InProceedings{Gupta_2019_CVPR_Workshops,
  author = {Gupta, Ritwik and Goodman, Bryce and Patel, Nirav and Hosfelt, Ricky and Sajeev, Sandra and Heim, Eric and Doshi, Jigar and Lucas, Keane and Choset, Howie and Gaston, Matthew},
  title = {Creating xBD: A Dataset for Assessing Building Damage from Satellite Imagery},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month = {June},
  year = {2019},
  pages = {10-17}
}
```

## 📋 License

**CC BY-NC-SA 4.0** - [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-nc-sa/4.0/)

Original dataset: [https://xview2.org/dataset](https://xview2.org/dataset)