File size: 11,230 Bytes
823cc2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83a89ff
 
 
 
 
 
 
a8a48f4
83a89ff
 
 
 
 
823cc2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
---
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.

## ๐Ÿ“Š Dataset Overview

This dataset contains satellite imagery paired with multi-language conversational annotations for disaster recognition tasks. It supports three languages: **English**, **Chinese (ไธญๆ–‡)**, and **Japanese (ๆ—ฅๆœฌ่ชž)**.

### Dataset Splits

- **Training Set (tier3)**: 9,168 image pairs โ†’ 55,008 conversations
- **Test Set**: 933 image pairs โ†’ 5,598 conversations
- **Total**: 10,101 image pairs โ†’ 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)

## ๐Ÿ—‚๏ธ Dataset Structure

### Downloadable Files (Available on HuggingFace)

The dataset is provided as compressed archives to facilitate downloading:

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

### After Extraction

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

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

## ๐ŸŒ Disaster Types

The dataset covers 6 types of natural disasters:

| Type | English | ไธญๆ–‡ | ๆ—ฅๆœฌ่ชž | Examples |
|------|---------|------|--------|----------|
| volcano | Volcano | ็ซๅฑฑ | ็ซๅฑฑ | Guatemala volcano |
| flooding | Flooding | ๆดชๆฐด | ๆดชๆฐด | Hurricane Florence, Hurricane Harvey |
| wind | Wind damage | ้ฃŽ็พ | ้ขจ็ฝ | Hurricane Matthew, Hurricane Michael |
| earthquake | Earthquake | ๅœฐ้œ‡ | ๅœฐ้œ‡ | Mexico earthquake |
| tsunami | Tsunami | ๆตทๅ•ธ | ๆดฅๆณข | Palu tsunami |
| fire | Fire | ็ซ็พ | ็ซ็ฝ | Santa Rosa wildfire, SoCal fire |

## ๐Ÿ–ผ๏ธ 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`

## ๐Ÿ’ฌ 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>\n่ฟ™ๅผ ๅ›พ็‰‡ไธญๅ‘็”Ÿไบ†็พๅฎณๅ—๏ผŸ"
    },
    {
      "from": "gpt",
      "value": "ๆ˜ฏ็š„๏ผŒ่ฟ™ๅผ ๅ›พ็‰‡ไธญๅ‘็”Ÿไบ†็พๅฎณใ€‚่ฟ™ๆ˜ฏ็พๅŽๅ›พๅƒใ€‚"
    },
    {
      "from": "human",
      "value": "่ฟ™ๅผ ๅ›พ็‰‡ไธญๅ‘็”Ÿไบ†ไป€ไนˆ็ฑปๅž‹็š„็พๅฎณ๏ผŸ"
    },
    {
      "from": "gpt",
      "value": "่ฟ™ๅผ ๅ›พ็‰‡ไธญๅ‘็”Ÿไบ†็ซๅฑฑ็พๅฎณใ€‚"
    }
  ]
}
```

### 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>\nใ“ใฎ็”ปๅƒใงใฏ็ฝๅฎณใŒ็™บ็”Ÿใ—ใฆใ„ใพใ™ใ‹๏ผŸ"
    },
    {
      "from": "gpt",
      "value": "ใฏใ„ใ€ใ“ใฎ็”ปๅƒใงใฏ็ฝๅฎณใŒ็™บ็”Ÿใ—ใฆใ„ใพใ™ใ€‚ใ“ใ‚Œใฏ็ฝๅฎณๅพŒใฎ็”ปๅƒใงใ™ใ€‚"
    },
    {
      "from": "human",
      "value": "ใ“ใฎ็”ปๅƒใงใฏใฉใฎใ‚ˆใ†ใช็จฎ้กžใฎ็ฝๅฎณใŒ็™บ็”Ÿใ—ใพใ—ใŸใ‹๏ผŸ"
    },
    {
      "from": "gpt",
      "value": "ใ“ใฎ็”ปๅƒใงใฏ็ซๅฑฑ็ฝๅฎณใŒ็™บ็”Ÿใ—ใพใ—ใŸใ€‚"
    }
  ]
}
```

## ๐Ÿ“š 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 kmยฒ of imagery from 15 countries.

## ๐Ÿ”— 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/)

## ๐Ÿ“‹ License

This derivative dataset follows the original license:

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

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

## ๐ŸŽฏ 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

## ๐Ÿ“ฆ 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... 
โœ… 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
```

## ๐Ÿ“š 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}
}
```

## ๐Ÿ“‹ 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)