Skip to content

Update README.md #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
priyansshi-i wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update README.md #2

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 21 additions & 21 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,16 +1,16 @@
# 🚀 YOLOv8 Space Station Object Detection
# YOLOv8 Space Station Object Detection

A complete object detection pipeline using YOLOv8 to detect **Toolbox**, **Oxygen Tank**, and **Fire Extinguisher** in space station environments using synthetic data from Duality AI Falcon platform.

## 🎯 Project Goals
## Project Goals

- Achieve **≥90% mAP@0.5** accuracy
- Robust detection under varying lighting conditions
- Handle occlusions and partial visibility
- Real-time inference capabilities
- Comprehensive evaluation and visualization

## 📋 Table of Contents
## Table of Contents

- [Features](#-features)
- [Installation](#-installation)
Expand All @@ -22,31 +22,30 @@ A complete object detection pipeline using YOLOv8 to detect **Toolbox**, **Oxyge
- [Configuration](#-configuration)
- [Troubleshooting](#-troubleshooting)

## ✨ Features

### 🎯 Core Functionality
## Features
### Core Functionality
- **YOLOv8 Training Pipeline** with hyperparameter optimization
- **Data Augmentation** (mosaic, HSV, flip, rotation, scaling)
- **Comprehensive Evaluation** (mAP@0.5, confusion matrix, per-class metrics)
- **Failure Case Analysis** for model improvement
- **Real-time Web Application** with Streamlit
- **Model Optimization Strategies** for accuracy improvement

### 📊 Analytics & Visualization
### Analytics & Visualization
- Training curves and loss plots
- Confusion matrix visualization
- Per-class performance metrics
- Dataset distribution analysis
- Failure case documentation

### 🔧 Technical Features
### Technical Features
- Modular and clean code architecture
- Comprehensive logging and error handling
- GPU/CPU support with automatic device detection
- Configurable hyperparameters via YAML
- Model checkpointing and resume training

## 🚀 Installation
## Installation

### Prerequisites
- Python 3.8+
Expand Down Expand Up @@ -91,7 +90,7 @@ mkdir -p runs/{train,val}
mkdir -p logs models results
```

## 📁 Dataset Preparation
## Dataset Preparation

### Dataset Structure
```
Expand Down Expand Up @@ -139,7 +138,7 @@ python data_utils.py --action split_dataset --images-dir raw_images --labels-dir
python data_utils.py --action visualize --images-dir dataset/train/images --labels-dir dataset/train/labels
```

## 🎯 Training
## Training

### Basic Training
```bash
Expand Down Expand Up @@ -173,7 +172,7 @@ Edit `config.yaml` to customize:
- **Training summary**: `training_summary.txt`
- **Logs**: `training.log`

## 📊 Evaluation
## Evaluation

### Model Evaluation
```bash
Expand All @@ -199,7 +198,7 @@ python predict.py --model runs/train/yolov8_training/weights/best.pt --images da
- **Failure cases**: `failure_cases.json`
- **Optimization recommendations**: `optimization_recommendations.txt`

## 🌐 Web Application
## Web Application

### Launch Streamlit App
```bash
Expand All @@ -219,7 +218,7 @@ streamlit run app.py
4. View detection results and statistics
5. Analyze performance in the analytics tab

## 📁 Project Structure
## Project Structure

```
space-station-object-detection/
Expand All @@ -243,7 +242,7 @@ space-station-object-detection/
└── results/ # Evaluation results
```

## ⚙️ Configuration
## Configuration

### Key Configuration Parameters

Expand Down Expand Up @@ -280,7 +279,7 @@ names:
2: Fire Extinguisher
```

## 🎯 Model Optimization Strategies
## Model Optimization Strategies

### For Achieving ≥90% mAP@0.5

Expand Down Expand Up @@ -370,26 +369,26 @@ python data_utils.py --action analyze --dataset-dir dataset
| YOLOv8m | 90-94% | 25.9 | 25.9 |
| YOLOv8l | 92-96% | 43.7 | 43.7 |

## 🤝 Contributing
## Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

## 📄 License
## License

This project is licensed under the MIT License - see the LICENSE file for details.

## 🙏 Acknowledgments
## Acknowledgments

- **Ultralytics** for YOLOv8 implementation
- **Duality AI** for Falcon synthetic data platform
- **Streamlit** for web application framework
- **OpenCV** for computer vision utilities

## 📞 Support
## Support

For questions and support:
- Create an issue on GitHub
Expand All @@ -398,4 +397,5 @@ For questions and support:

---

**Happy detecting! 🚀🔍**

**Happy detecting!**