28 lines
705 B
Markdown
28 lines
705 B
Markdown
|
# Sidewalk Accessibility Audit
|
||
|
|
|
||
|
|
VIMS instance for sidewalk-accessibility.
|
||
|
|
|
||
|
|
## Related Article
|
||
|
|
[/insights/how-to-measure-urban-decay/](https://landvex.com/insights/how-to-measure-urban-decay/)
|
||
|
|
|
||
|
|
## Anomaly Classes
|
||
|
|
- cracked_surface
|
||
|
|
- missing_curb_ramp
|
||
|
|
- obstruction
|
||
|
|
- uneven_surface
|
||
|
|
- narrow_path
|
||
|
|
|
||
|
|
## 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/sidewalk-accessibility/predict`
|
||
|
|
- WebSocket: `ws://host/ws/sidewalk-accessibility/alerts`
|