Skip to main content

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

  1. Clone the repository:

    git clone https://github.com/ai4ce/UNav_Server.git
    cd UNav_Server
    
  2. Build the Cython extensions in place:

    python setup_so.py build_ext --inplace
    
  3. Create the source distribution and wheel:

    python setup.py sdist bdist_wheel
    
  4. Upload the package to PyPI:

    twine upload --verbose dist/*
    

User Installation

Users can directly install UNav from PyPI:

pip install unav

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

unav-0.1.33.tar.gz (3.6 MB view details)

Uploaded Source

Built Distribution

unav-0.1.33-py3-none-any.whl (3.7 MB view details)

Uploaded Python 3

File details

Details for the file unav-0.1.33.tar.gz.

File metadata

  • Download URL: unav-0.1.33.tar.gz
  • Upload date:
  • Size: 3.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.8.16

File hashes

Hashes for unav-0.1.33.tar.gz
Algorithm Hash digest
SHA256 d51178c5c6646e9213f9c178ddfd7650c80db4bf7f831a07b2a7c59c64bff5ec
MD5 a52cf498d64e9e7ffcb0e5656d16f3ca
BLAKE2b-256 df7a85cc15df4f1b361fa741fe3f8cf1b238897d05dcbabf5e1a0766d25a30de

See more details on using hashes here.

File details

Details for the file unav-0.1.33-py3-none-any.whl.

File metadata

  • Download URL: unav-0.1.33-py3-none-any.whl
  • Upload date:
  • Size: 3.7 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.8.16

File hashes

Hashes for unav-0.1.33-py3-none-any.whl
Algorithm Hash digest
SHA256 8b92a499f4880b6cbf82986827ee914b16b4558c8179b32705a6edf99bc5e545
MD5 9265d811558ebb65a355f1101aca56f3
BLAKE2b-256 a94f7bc77c75ef8afd93a5b55791ffce15978577a280c4268fc5e42ad2996b99

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page