Model Card for rebotnix/rb_licenseplate
🚗 License Plate Detection in Street-Level Imagery – Trained by KINEVA, Built by REBOTNIX, Germany Current State: in production and re-training.
This object detection model identifies license plates in street-level imagery such as from car-mounted cameras, city surveillance, or mapping vehicles (similar to Google Street View). It is trained on a diverse dataset covering a wide range of vehicle types, plate styles and urban/rural environments. Applications include privacy protection (blurring plates), smart parking systems, urban regulation enforcement and mapping data anonymization.
Developed and maintained by REBOTNIX, Germany, https://rebotnix.com
About KINEVA
KINEVA® is an automated training platform based on the MCP Agent system. It regularly delivers new visual computing models, all developed entirely from scratch. This approach enables the creation of customized models tailored to specific client requirements, which can be retrained and re-released as needed. The platform is particularly suited for applications that demand flexibility, adaptability, and technological precision—such as industrial image processing, smart city analytics, or automated object detection.
KINEVA is continuously evolving to meet the growing demands in the fields of artificial intelligence and machine vision. https://rebotnix.com/en/kineva
🚗 Example Predictions
| Input Image | Detection Result |
|---|---|
 |
 |
 |
 |
| (More example visualizations coming soon) |
Model Details
- Architecture: RF-DETR (custom training head with optimized anchor boxes)
- Task: Object Detection (License Plate class)
- Trained on: REBOTNIX Street Imagery License Plate Dataset (proprietary)
- Format: PyTorch
.pth+ ONNX and trt export available on request - Backbone: EfficientNet B3 (adapted)
- Training Framework: PyTorch + RF-DETR + custom augmentation
Chart
Dataset
The training dataset consists of street-level camera imagery collected from:
- Open-source urban street datasets
- Licensed datasets from car-mounted camera surveys
- Custom annotated bounding boxes by REBOTNIX team
The model was trained to be robust across:
- Varying plate sizes and shapes (European, US, Asian formats)
- Different viewing angles (head-on, side, tilted)
- Lighting conditions (sunny, cloudy, shaded)
- Partial occlusions (e.g., by dirt, trees, reflections)
Intended Use
| ✅ Intended Use | ❌ Not Intended Use |
|---|---|
| License plate blurring for privacy | License plate recognition (OCR not included) |
| Anonymization of street imagery | Detecting plates at night (unsupported) |
| Smart city privacy monitoring | Reading handwritten or damaged plates |
Limitations
- Model detects plates but does not recognize or read plate numbers.
- Performance may decrease with nighttime images.
- Small or heavily obscured plates may be missed.
Usage Example
import supervision as sv
from PIL import Image
from rfdetr import RFDETRBase
model_path= "./rb_licenseplate.pth"
CLASS_NAMES = ["licenseplate"]
model = RFDETRBase(pretrain_weights=model_path,num_classes=len(CLASS_NAMES))
image_path = "./example_licenseplate.jpg"
image = Image.open(image_path)
detections = model.predict(image, threshold=0.35)
labels = [
f"{CLASS_NAMES[class_id]} {confidence:.2f}"
for class_id, confidence
in zip(detections.class_id, detections.confidence)
]
print(labels)
annotated_image = image.copy()
annotated_image = sv.BoxAnnotator().annotate(annotated_image, detections)
annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels)
annotated_image.save("./output_1.jpg")
Contact
📫 For commercial use or re-training this model support, or dataset access, contact:
REBOTNIX
✉️ Email: communicate@rebotnix.com
🌐 Website: https://rebotnix.com
License
This model is released under CC-BY-NC-SA unless otherwise noted. For commercial licensing, please reach out to the contact email.