项目作者: redlogo

项目描述 :
High FPS live stream Raspberry Pi cam with object detection by Google Coral EdgeTPU
高级语言: Python
项目地址: git://github.com/redlogo/RPi-Stream.git
创建时间: 2020-04-22T22:37:19Z
项目社区:https://github.com/redlogo/RPi-Stream

开源协议:MIT License

下载


Fast Raspberry Pi Stream Object Detection - Multi Platform

Introduction

Live camera stream: from Raspberry Pi to your local computer host.

Live object detection: with Coral EdgeTPU on host side.

High FPS: 35-45, depending mostly on network condition.

Multiple platform: ready for Ubuntu, MacOS, Windows.

Application scenario: AI-powered surveillance camera.

Video Tutorial

  • A preview of this project
  • preview

    Preparation and Environment

  • Raspberry Pi, latest RPi4 is recommended.
  • Latest Raspbian is recommended for RPi.
  • A camera for RPi, such as RPi camera module V2.
  • A local computer host with usb 3.0 port:
    • Ubuntu, MacOS, Windows are supported.
  • Coral EdgeTPU. USB version is recommended.
  • Python virtual env is recommended:
  • IDE such as PyCharm is recommended for host.

    Installation

    Clone this repository on both RPi and computer host sides:
    1. git clone https://github.com/redlogo/RPi-Stream.git
    Install libs needed for Raspberry Pi:
    1. bash RPi-requirements.sh
    Install libs required for local computer with EdgeTPU unplugged:
    1. # Ubuntu
    2. bash computer-hose-requirements-linux.sh
    3. # MacOS
    4. bash computer-host-requirements-macos.sh
    5. # Windows
    6. check out computer-host-requirements-windows.txt
    Plug USB EdgeTPU into the host usb 3.0 port.

    Usage

    Edit on RPi side, change sender_stream.py:
    1. # line 20, change it to your local computer host ip
    2. target_ip = '192.168.7.33'
    Firstly execute script on RPi side:
    1. python3 sender_stream.py
    Secondly execute script on local computer host side:
    1. python3 receiver_stream_object_detection.py
    2. (Windows: try 'python' w/o '3' or use IDE instead of Windows CMD)
    To exit, firstly terminate RPi side, then host side.

    Coding Style

    General Python 3 Coding style.

    Version

    1.0 - April 2020.

    Author

    redlogo

    References and Acknowledgements

  • Coral EdgeTPU
  • Python library of imagezmq
  • A brilliant project by EdjeElectronics

    License

    MITCopyright © 2020 redlogo