Skip to main content

A mmWave radar data processing library

Project description

PreSense mmWave Package

Version Documentation

This is PreSense team's implementation of TI mmwave radar DSP stack and some demos. We are grateful for TI, TI's e2e forum and other people's help to make this happen. Please star us if you like this repository and please consider citing this repo if you used it in your research.

The toolbox is modularized into separate steps

  1. Reading raw ADC data.
  2. Preprocessing data in DSP stack.
  3. Utilizing preprocessed data for tracking, clustering and machine learning.
  4. Different demo implementations from TI and our own explorations.

Documentation

Contact

Directory Structure

.
├── data                    # Small size sample data.
├── demo                    # Python implementations of TI demos.
├── docs                    # Documentation for mmwave pacakge and hardware setup.
├── mmwave                  # mmwave package including all the DSP, tracking, etc algorithms.
├── PreSense Applied radar  # Jupyter notebook series explaining how apply radar concepts to real data
├── scripts                 # Various setup scripts for mmwavestudio, etc
├── .gitignore
├── LICENSE
├── README.md
├── requirements.txt        # Required dependencies to run this package.
└── setup.py                # Install mmwave package.

Current Roadmap for this package

  • Code refactoring for better API support.
  • More tutorials to help people get started on FMCW radar.
  • More AoA methods support.
  • More noise removal algorithms.

Future Plan

  1. Hardware Abstraction Layer, e.g. hardware-agnostic data reading or processing.
  2. ML on radar (classification, detection, tracking, etc).

Installation

Pip installation

Coming soon

Debug Mode

git clone https://github.com/presenseradar/openradar
cd openradar
pip install -r requirements.txt
python setup.py develop

Uninstallation

pip uninstall mmwave

Example Import and Usage

import mmwave as mm
from mmwave.dataloader import DCA1000

dca = DCA1000()
adc_data = dca.read()
radar_cube = mm.dsp.range_processing(adc_data)

Citation

Please cite OpenRadar in your publications if it helps your research. Here is an example BibTeX entry:

@misc{openradar2019,
  author = {Pan, Edwin and Tang, Jingning and Kosaka, Dash and Yao, Ruihao and Gupta, Arjun},
  title = {OpenRadar},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/presenseradar/openradar}}
}

Acknowledgement

The PreSense team wants to thank Prof. Sanjay Patel, without whom this project wouldn't be possible. We are also grateful for the generous sponsorship from The IBM-ILLINOIS Center for Cognitive Computing Systems Research (C3SR) and the guidance/leadership from Jinjun Xiong of IBM and Prof. Wen-Mei Hwu. Special thanks to Prof. Haitham Hassanieh and Prof. Minh M. Do for the techical advice and Texas Instruments™ for the hardware support.

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

openradar-1.0.1.tar.gz (1.9 MB view details)

Uploaded Source

Built Distribution

openradar-1.0.1-py3-none-any.whl (71.5 kB view details)

Uploaded Python 3

File details

Details for the file openradar-1.0.1.tar.gz.

File metadata

  • Download URL: openradar-1.0.1.tar.gz
  • Upload date:
  • Size: 1.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.4.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.5

File hashes

Hashes for openradar-1.0.1.tar.gz
Algorithm Hash digest
SHA256 a571cd3972973f7647ab1e8c40bc5c654f484b1829b09f7bc33e96def0eb9993
MD5 f1ce6cce40ab13ac58720ca01e490787
BLAKE2b-256 508a3825b8a760534fbae1aff27d45b48624a0db060aa9fdb33c10ad020c8069

See more details on using hashes here.

File details

Details for the file openradar-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: openradar-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 71.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.4.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.5

File hashes

Hashes for openradar-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 8c1820367472fa46752dfb6df95228cddec98729250c007815097607cad0ff74
MD5 ad9c38397df0a42f139b7b488f92d360
BLAKE2b-256 c95cb50466c02b7732a03fac5f2b6c89394ca39470affd6a9751fa3d517ce46d

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