Model Card for rebotnix/rb_graffiti
🖍️ Graffiti Detection on Urban Surfaces – Trained by KINEVA, Built by REBOTNIX, Germany Current State: in production and re-training.
This object detection model identifies graffiti on urban surfaces such as walls, fences, and public structures. It has been trained on a curated dataset containing diverse graffiti styles, various urban environments, and lighting conditions. The model is designed to support research and automation use-cases in urban monitoring, smart city applications, and security.
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 (Graffiti class)
- Trained on: REBOTNIX Graffiti 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 high-resolution urban imagery collected from:
- Open-source cityscapes
- Licensed urban surveillance footage
- Custom annotated bounding boxes by REBOTNIX team
The model was trained to be robust across:
- Different surfaces (walls, fences, public structures)
- Various lighting conditions (daylight, night, low-light)
- Different graffiti styles (tags, murals, street art)
- Various urban backgrounds (residential, commercial, industrial)
Intended Use
| ✅ Intended Use | ❌ Not Intended Use |
|---|---|
| Urban surveillance | Illegal activity detection |
| Graffiti removal planning | Non-urban object detection |
| Public infrastructure maintenance | Private property monitoring |
Limitations
- May miss graffiti on non-visible or heavily obscured surfaces
- Less effective on small or intricate graffiti designs
- Not optimized for non-urban environments
Usage Example
import supervision as sv
from PIL import Image
from rfdetr import RFDETRBase
model_path= "./rb_graffiti.pth"
CLASS_NAMES = ["graffiti"]
model = RFDETRBase(pretrain_weights=model_path,num_classes=len(CLASS_NAMES))
image_path = "./example_graffiti.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: [email protected]
🌐 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.