Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,34 @@ language:
|
|
| 5 |
base_model:
|
| 6 |
- Ultralytics/YOLO26
|
| 7 |
pipeline_tag: image-segmentation
|
| 8 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
base_model:
|
| 6 |
- Ultralytics/YOLO26
|
| 7 |
pipeline_tag: image-segmentation
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Car Damage Type Model
|
| 11 |
+
|
| 12 |
+
This repository contains the Car Damage Type Detection model. It uses a YOLO architecture to identify and classify specific types of physical damage on vehicles.
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
|
| 16 |
+
- **Model type:** Object Detection and Segmentation (YOLOv26 via Ultralytics)
|
| 17 |
+
- **Task:** Vehicle Damage Type Detection
|
| 18 |
+
|
| 19 |
+
## Intended Use
|
| 20 |
+
|
| 21 |
+
This model is intended for detecting and classifying physical damage on vehicles in images or video frames. It can be used as a standalone detector or integrated into a larger pipeline.
|
| 22 |
+
|
| 23 |
+
## Detected Classes
|
| 24 |
+
|
| 25 |
+
The model detects and localizes the following 6 classes of damage:
|
| 26 |
+
- `0`: **crack** - Cracks on car body panels or lights.
|
| 27 |
+
- `1`: **dent** - Indentations or structural dents.
|
| 28 |
+
- `2`: **glass shatter** - Shattered or completely broken glass (windshields, windows).
|
| 29 |
+
- `3`: **lamp broken** - Broken headlights or tail lights.
|
| 30 |
+
- `4`: **scratch** - Paint scratches or surface abrasions.
|
| 31 |
+
- `5`: **tire flat** - Deflated or flat tires.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|