---
license: cc-by-nc-sa-4.0
extra_gated_fields:
  full_name:
    type: text
    label: What is your full name?
    required: true
  email:
    type: text
    label: What is your email address?
    required: true
  company:
    type: text
    label: Which company or institution are you affiliated with?
    required: false
  intended_use:
    type: text
    label: Please describe your intended use of this model.
    required: true
  agreement:
    type: text
    label: >-
      Type "I agree" to confirm you have read and accept the license and usage
      conditions.
    required: true
tags:
- objectdetection
- ship
- maritime
- ai
---

---

![Example input](./kineva_ship_bg.jpg)


# Model Card for `rebotnix/rb_ship`

> 🚢  **Ship Detection in Maritime and Aerial Imagery** – Trained by KINEVA, Built by REBOTNIX, Germany
Current State: in production and re-training.

---
This object detection model identifies **ships and vessels in maritime and coastal imagery**. It was trained on a custom-curated dataset with a broad range of ship types, sea conditions, backgrounds (negatives) and geographic environments. The model supports applications in **coastal monitoring**, **maritime logistics**, **port authority surveillance**, and **marine environmental studies**.

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

<!-- Placeholder for inference visualization images -->
| Input Image | Detection Result |
|-------------|------------------|
| <img src="./example_ship1.jpg" width="300"/> | <img src="./output_1.jpg" width="300"/> |
| <img src="./example_ship2.jpg" width="300"/> | <img src="./output_2.jpg" width="300"/> |
_(More example visualizations coming soon)_

---

## Model Details

- **Architecture**: RF-DETR *(custom training head with optimized anchor boxes)*
- **Task**: Object Detection (Ship class)
- **Trained on**: REBOTNIX Aerial Ship Dataset (proprietary)
- **Format**: PyTorch `.pth` + ONNX and trt export available on request
- **Backbone**: EfficientNet B3 (adapted)
- **Training Framework**: PyTorch + RF-DETR + custom augmentation

---

## Chart
![Example input](./chart.jpg)

## Dataset

The training dataset consists of **high-resolution aerial imagery** collected from:
- Open-source satellite archives
- Licensed drone surveys
- Custom annotated bounding boxes by REBOTNIX team

The model was trained to be robust across:
- Different vessel sizes (from small boats to cargo ships)
- Varied sea conditions (calm, stormy, cluttered)
- Partial occlusions
- Complex scenes (ports, coasts, open sea)

---

## Intended Use

| ✅ Intended Use | ❌ Not Intended Use |
|----------------|---------------------|
| Port traffic analysis | Naval combat systems |
| Maritime infrastructure monitoring | Submerged object detection |
| Shipping route analytics | Nighttime IR surveillance (unsupported) |

---

## Limitations

- False positives may occur in **heavy fog or extreme wave conditions**
- May confuse small leisure boats with environmental debris
- Designed for **daylight and optical imagery only**

---

## Usage Example

```python
import supervision as sv
from PIL import Image
from rfdetr import RFDETRBase

model_path= "./rb_ship.pth"
CLASS_NAMES = ["ship"]
model = RFDETRBase(pretrain_weights=model_path,num_classes=len(CLASS_NAMES))

image_path = "./example_ship1.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](mailto:communicate@rebotnix.com)  
🌐 Website: [https://rebotnix.com](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.

---