{"id":13586581,"url":"https://github.com/redlogo/RPi-Stream","last_synced_at":"2025-04-07T18:34:03.891Z","repository":{"id":146085419,"uuid":"258035793","full_name":"redlogo/RPi-Stream","owner":"redlogo","description":"High FPS live stream Raspberry Pi cam with object detection by Google Coral EdgeTPU","archived":false,"fork":false,"pushed_at":"2020-04-25T05:44:16.000Z","size":4546,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-02-14T21:38:09.524Z","etag":null,"topics":["coral-tpu","edge-tpu","edgetpu","object-detection","raspberry-pi"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/redlogo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-04-22T22:37:19.000Z","updated_at":"2024-08-01T16:32:35.836Z","dependencies_parsed_at":null,"dependency_job_id":"3d5ff171-b1fe-4ca1-865a-07bab16f8bc9","html_url":"https://github.com/redlogo/RPi-Stream","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/redlogo%2FRPi-Stream","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/redlogo%2FRPi-Stream/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/redlogo%2FRPi-Stream/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/redlogo%2FRPi-Stream/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/redlogo","download_url":"https://codeload.github.com/redlogo/RPi-Stream/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247707698,"owners_count":20982828,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["coral-tpu","edge-tpu","edgetpu","object-detection","raspberry-pi"],"created_at":"2024-08-01T15:05:39.776Z","updated_at":"2025-04-07T18:34:03.548Z","avatar_url":"https://github.com/redlogo.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Fast Raspberry Pi Stream Object Detection - Multi Platform\n## Introduction\nLive camera stream: from Raspberry Pi to your local computer host.\n\u003cbr\u003eLive object detection: with Coral EdgeTPU on host side.\n\u003cbr\u003eHigh FPS: 35-45, depending mostly on network condition.\n\u003cbr\u003eMultiple platform: ready for Ubuntu, MacOS, Windows.\n\u003cbr\u003eApplication scenario: AI-powered surveillance camera.\n\n## Video Tutorial\n* [A preview of this project](https://www.youtube.com/watch?v=PCdNH4zSNug)\n* [![preview](meta/preview.png)](https://www.youtube.com/watch?v=PCdNH4zSNug)\n## Preparation and Environment\n* Raspberry Pi, [latest RPi4](https://www.raspberrypi.org/products/raspberry-pi-4-model-b/) is recommended.\n* Latest [Raspbian](https://www.raspberrypi.org/downloads/raspbian/) is recommended for RPi. \n* A camera for RPi, such as [RPi camera module V2](https://www.raspberrypi.org/products/camera-module-v2/).\n* A local computer host with usb 3.0 port:\n  * Ubuntu, MacOS, Windows are supported.\n* [Coral EdgeTPU](https://coral.ai/products/accelerator/). USB version is recommended.\n* Python virtual env is recommended:\n  * virtualenv (python3.7) for RPi.\n  * [Anaconda / Conda](https://www.anaconda.com/) (python3.7) for host.\n* IDE such as [PyCharm](https://www.jetbrains.com/pycharm/) is recommended for host.\n## Installation\nClone this repository on both RPi and computer host sides:\n```\ngit clone https://github.com/redlogo/RPi-Stream.git\n```\nInstall libs needed for Raspberry Pi:\n```\nbash RPi-requirements.sh\n```\nInstall libs required for local computer with EdgeTPU unplugged:\n```\n# Ubuntu\nbash computer-hose-requirements-linux.sh\n# MacOS\nbash computer-host-requirements-macos.sh\n# Windows\ncheck out computer-host-requirements-windows.txt\n```\nPlug USB EdgeTPU into the host usb 3.0 port.\n## Usage\nEdit on RPi side, change sender_stream.py:\n```\n# line 20, change it to your local computer host ip\ntarget_ip = '192.168.7.33'  \n```\nFirstly execute script on RPi side:\n```\npython3 sender_stream.py\n```\nSecondly execute script on local computer host side:\n```\npython3 receiver_stream_object_detection.py\n(Windows: try 'python' w/o '3' or use IDE instead of Windows CMD)\n```\nTo exit, firstly terminate RPi side, then host side.\n## Coding Style\nGeneral Python 3 Coding style.\n## Version\n1.0 - April 2020.\n## Author\nredlogo\n## References and Acknowledgements\n* [Coral EdgeTPU](https://coral.ai/)\n* [Python library of imagezmq](https://github.com/jeffbass/imagezmq)\n* [A brilliant project by EdjeElectronics](https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi)\n## License\nMIT\n## Copyright\nCopyright © 2020 redlogo","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fredlogo%2FRPi-Stream","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fredlogo%2FRPi-Stream","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fredlogo%2FRPi-Stream/lists"}