EasySLAM
EasySLAM is a production-ready Python package that makes Simultaneous Localization and Mapping (SLAM) accessible to beginners while providing advanced features for researchers and professionals.
🚀 Features
Core SLAM Algorithms
- ORB-SLAM: Feature-based visual SLAM with loop closure
- FastSLAM: Particle filter SLAM for mobile robots
- GraphSLAM: Graph optimization-based SLAM
- Visual-Inertial SLAM: Camera + IMU fusion
- RGB-D SLAM: Depth camera SLAM with Open3D
Sensor Support
- Webcam: Standard USB cameras
- RealSense: Intel RealSense depth cameras
- Stereo Cameras: Dual camera setups
- LiDAR: 3D laser scanners
- Datasets: TUM, KITTI, custom datasets
Advanced Features
- Semantic Mapping: Object detection and labeling
- Sensor Fusion: Multi-sensor data fusion with EKF
- Map Merging: Combine multiple SLAM sessions
- Performance Profiling: Real-time monitoring and optimization
- GUI Interface: PyQt6-based visualization tool
Output Formats
- Trajectory: TUM format, JSON, CSV
- Point Clouds: PLY, PCD formats
- 3D Maps: Mesh reconstruction
- Performance Reports: Detailed analytics
📦 Installation
From PyPI (Recommended)
pip install easy-slam
From Source
git clone https://github.com/Sherin-SEF-AI/EasySLAM.git
cd EasySLAM
pip install -e .
Optional Dependencies
# For 3D visualization
pip install easy-slam[3d]
# For RealSense cameras
pip install easy-slam[realsense]
# For advanced optimization
pip install easy-slam[g2o]
# For development
pip install easy-slam[dev]
🎯 Quick Start
Basic Usage
from easy_slam import EasySLAM
# Initialize with webcam
slam = EasySLAM(camera=0, algorithm='orb_slam')
slam.start()
Advanced Usage
from easy_slam import EasySLAM
# Configure with advanced features
slam = EasySLAM(
camera='realsense',
algorithm='rgbd_slam',
semantic_mapping=True,
sensor_fusion=True,
save_trajectory=True,
output_dir='./results'
)
# Start SLAM processing
slam.start()
# Get results
trajectory = slam.get_trajectory()
map_data = slam.get_map()
GUI Interface
# Launch the GUI
easy-slam-gui
# Or run programmatically
python -m easy_slam.gui
📖 Documentation
API Reference
EasySLAM Class
class EasySLAM:
def __init__(self,
camera: Union[int, str] = 0,
config: Optional[str] = None,
mode: str = 'realtime',
algorithm: str = 'orb_slam',
visualization: bool = True,
save_trajectory: bool = False,
output_dir: str = "./results",
**kwargs):
"""
Initialize SLAM system.
Args:
camera: Camera index, path, or sensor type
config: Optional path to YAML config file
mode: 'realtime' or 'offline'
algorithm: SLAM algorithm name
visualization: Enable 3D visualization
save_trajectory: Save trajectory to file
output_dir: Directory for output files
"""
Available Algorithms
'orb_slam': ORB-SLAM (default)'fastslam': FastSLAM particle filter'graphslam': Graph optimization SLAM'visual_inertial': Visual-inertial SLAM'rgbd_slam': RGB-D SLAM
Available Cameras
0, 1, 2...: Webcam indices'webcam': Default webcam'realsense': Intel RealSense'stereo': Stereo camera setup'lidar': LiDAR sensor'path/to/dataset': Dataset file or directory
Configuration
Create a YAML configuration file:
slam:
algorithm: orb_slam
mode: realtime
sensor:
type: webcam
resolution: [640, 480]
fps: 30
algorithm:
max_features: 2000
scale_factor: 1.2
levels: 8
visualization:
enabled: true
update_rate: 10
output:
save_trajectory: true
directory: "./results"
performance:
threading: true
memory_limit: "2GB"
🎮 GUI Features
The EasySLAM GUI provides:
- Real-time video display
- 2D trajectory visualization
- 3D map view
- Feature point visualization
- Performance monitoring
- Live log output
- Camera and algorithm selection
- Advanced feature toggles
🔧 Advanced Features
Semantic Mapping
slam = EasySLAM(
camera=0,
semantic_mapping=True,
semantic_model='yolov8'
)
Sensor Fusion
slam = EasySLAM(
camera='realsense',
sensor_fusion=True,
imu_enabled=True
)
Map Merging
slam = EasySLAM(
camera=0,
map_merging=True,
loop_closure=True
)
📊 Performance
EasySLAM is optimized for real-time performance:
- 30+ FPS on standard webcams
- Memory efficient for long sessions
- Multi-threaded processing
- GPU acceleration support (optional)
🤝 Contributing
We welcome contributions! Please see our Contributing Guidelines for details.
Development Setup
git clone https://github.com/Sherin-SEF-AI/EasySLAM.git
cd EasySLAM
pip install -e .[dev]
pytest tests/
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- OpenCV for computer vision algorithms
- Open3D for 3D processing
- PyQt6 for GUI framework
- NumPy and SciPy for numerical computing
📞 Support
- Issues: GitHub Issues
- Email: sherin.joseph2217@gmail.com
- Documentation: GitHub Wiki
🔗 Links
- Source Code: https://github.com/Sherin-SEF-AI/EasySLAM
- PyPI Package: https://pypi.org/project/easy-slam/
- Documentation: https://github.com/Sherin-SEF-AI/EasySLAM/wiki
Made with ❤️ by sherin joseph roy
Metadata
Release files for easy-slam 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| easy_slam-0.1.0.tar.gz | 46.2 kB | Without provenance | Details for easy_slam-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| easy_slam-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for easy_slam-0.1.0-py3-none-any.whl |
Total release size: 94.9 kB
Release files / easy_slam-0.1.0.tar.gz
| Download URL | easy_slam-0.1.0.tar.gz |
|---|---|
| Size | 46.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
26f58f763c62db2781ba322a47cc3c0f9d846ff5d5c39149b0b8e5b010a6f753
|
|
BLAKE2b-256 checksum How to use checksums |
fc6872f6653f5f0a39ba7825e1336ab9a5c2572e810d328f159876a5964432ca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.3
|
Release files / easy_slam-0.1.0-py3-none-any.whl
| Download URL | easy_slam-0.1.0-py3-none-any.whl |
|---|---|
| Size | 48.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4f84e7ee791d3c76d206fc8e41882e65287ea7e09cf880938dc748dbb7c413ea
|
|
BLAKE2b-256 checksum How to use checksums |
ab796338c68ee4bae9415e37a4c2d9de0dff87e2ccbd868136cd3a0bccea0a90
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.3
|
Security for easy-slam 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.