Space Debris Yolov8
A YOLOv8-powered deep learning system for detecting space debris and satellites in orbital imagery — with real-time collision risk assessment.
Source du modèle
- Type
- Other
- Taille du fichier
- 5,96 MB
- Version
- vRevision 3ed855d
- Mis à jour
- 27 sept. 2026
- Téléchargements
- 7
- Tâches
- Détection d'objets
- Source
- Hugging Face
Extrait de la source
A YOLOv8-powered deep learning system for detecting space debris and satellites in orbital imagery — with real-time collision risk assessment.
Sources
1 source
Sources
1 sourceVérifié 27 sept.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: mit tags: - object-detection - yolov8 - space-debris - computer-vision - ultralytics language: - en --- <div align="center"> # 🛰️ Space Debris Detection & Risk Assessment **A YOLOv8-powered deep learning system for detecting space debris and satellites in orbital imagery — with real-time collision risk assessment.**      </div> --- ## 📌 Overview Space debris poses a significant risk to operational satellites and future space missions. This project uses **YOLOv8 object detection** trained on orbital imagery to identify and classify **Satellites** and **Debris** in real time, and assess the **collision risk level** based on detected debris count. The project includes a **Streamlit web application** for easy image upload and visualization, along with the complete training notebook used to develop the model. --- ## 🎯 Key Features | Feature | Description | |---|---| | 🛸 **Object Detection** | Detects Satellites and Debris using YOLOv8 | | 🎨 **Confidence Tiers** | Color-coded bounding boxes (🟢 High ≥ 0.80 / 🟡 Medium 0.50–0.80 / 🔴 Low < 0.50) | | 📊 **Risk Assessment** | Collision risk score: LOW / MEDIUM / HIGH based on debris count | | ⚙️ **Adjustable Threshold** | Sidebar slider to control detection confidence | | ⚡ **Fast Inference** | FP16 half-precision model for faster predictions | | 🖥️ **Web Interface** | Clean Streamlit UI — no coding required to use | --- ## 🧠 Model Performance > Trained for **30 epochs** on orbital imagery dataset using **YOLOv8 (Ultralytics v8.4.27)** | Metric | Score | |---|---| | **Precision** | 0.930 | | **Recall** | 0.926 | | **mAP@50** | 0.931 | | **mAP@50-95** | 0.750 | | **Image Size** | 640 × 640 | | **Classes** | Satellite, Debris | | **Precision (Storage)** | FP16 (Half) | --- ## 📦 Project Structure ``` space-debris-detection/ ├── app.py # Streamlit web application ├── space_debris_v2-1.ipynb # Model training & experimentation notebook ├──...
Source context: 7 downloads · 1 likes · Pipeline object-detection · Library ultralytics · Repo tanveeerr/space-debris-yolov8
