UNav is designed for helping navigation of visually impaired people
Project description
UNav
UNav is designed for helping navigation of visually impaired people. It leverages various features and algorithms to provide accurate localization and navigation assistance.
Features
- Global Feature Extraction: Using NetVLAD for image-based localization.
- Local Feature Extraction: Using SuperPoint and SuperGlue for detailed image matching.
- Navigation and Localization: Combines global and local features for accurate navigation.
Developer Installation
To install UNav as a developer, follow these steps:
Prerequisites
- Python 3.6 or higher
- Cython
- NumPy
- PyTorch
- OpenCV
- h5py
- scikit-image
Instructions
-
Clone the repository:
git clone https://github.com/ai4ce/UNav_Server.git cd UNav_Server
-
Build the Cython extensions in place:
python setup_so.py build_ext --inplace
-
Create the source distribution and wheel:
python setup.py sdist bdist_wheel
-
Upload the package to PyPI:
twine upload --verbose dist/*
User Installation
Users can directly install UNav from PyPI:
pip install unav
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
unav-0.1.36.tar.gz
(3.6 MB
view details)
Built Distribution
unav-0.1.36-py3-none-any.whl
(3.7 MB
view details)