28 lines
676 B
Markdown
28 lines
676 B
Markdown
|
# Graffiti Tracking & Removal
|
||
|
|
|
||
|
|
VIMS instance for graffiti-tracking.
|
||
|
|
|
||
|
|
## Related Article
|
||
|
|
[/insights/urban-growth-index-nordic/](https://landvex.com/insights/urban-growth-index-nordic/)
|
||
|
|
|
||
|
|
## Anomaly Classes
|
||
|
|
- new_graffiti
|
||
|
|
- tagging
|
||
|
|
- gang_symbols
|
||
|
|
- hate_speech
|
||
|
|
- property_damage
|
||
|
|
|
||
|
|
## Quick Start
|
||
|
|
|
||
|
|
1. Add training images to `data/raw/`
|
||
|
|
2. Annotate using LabelImg (YOLO format)
|
||
|
|
3. Run preprocessing: `python src/detector.py`
|
||
|
|
4. Train model: `python src/detector.py --train`
|
||
|
|
5. Run inference: `python src/detector.py --predict data/test/image.jpg`
|
||
|
|
|
||
|
|
## API
|
||
|
|
|
||
|
|
Once deployed, access via:
|
||
|
|
- REST: `POST /api/graffiti-tracking/predict`
|
||
|
|
- WebSocket: `ws://host/ws/graffiti-tracking/alerts`
|