{"id":20056008,"url":"https://github.com/zackakil/robo-videographer","last_synced_at":"2025-05-05T13:33:37.617Z","repository":{"id":165195045,"uuid":"73750024","full_name":"ZackAkil/robo-videographer","owner":"ZackAkil","description":"Project for a automatic videographer system for recording sports matches.","archived":false,"fork":false,"pushed_at":"2019-08-19T14:24:23.000Z","size":95717,"stargazers_count":13,"open_issues_count":1,"forks_count":5,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-05-04T01:54:09.884Z","etag":null,"topics":["camera","machine-vision","neural-network","raspberry-pi","servo-controller","sklearn"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ZackAkil.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2016-11-14T21:49:34.000Z","updated_at":"2024-11-04T17:13:11.000Z","dependencies_parsed_at":null,"dependency_job_id":"ac16ef9a-f3e6-4181-8299-e7a8599e2ba8","html_url":"https://github.com/ZackAkil/robo-videographer","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/ZackAkil%2Frobo-videographer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZackAkil%2Frobo-videographer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZackAkil%2Frobo-videographer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZackAkil%2Frobo-videographer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZackAkil","download_url":"https://codeload.github.com/ZackAkil/robo-videographer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252506674,"owners_count":21759095,"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":["camera","machine-vision","neural-network","raspberry-pi","servo-controller","sklearn"],"created_at":"2024-11-13T12:51:00.036Z","updated_at":"2025-05-05T13:33:32.609Z","avatar_url":"https://github.com/ZackAkil.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Robo Videographer\nProject for a automatic videographer system for recording sports matches.\n\n## Technical objective\nThe aim is to create a computer vision tracking system that can run on a Raspberry Pi using the camera module that tracks the action happening on a rugby pitch.\n\n## Implimentation goal\nThe final aim is to use the system to record a tag rugby matches with no human intervention. \n\n## Technology to use\n* Raspberry Pi\n* Raspberry Pi Camera module\n* OpenCV | SimpleCV\n* Video camera\n* Servo\n\n## Intial Design\n1. Get OpenCV/SimpleCV working on the Raspberry Pi with the camera.\n2. Build a program that tracks the pixel activity.\n3. Output activity value to a servo position.\n\n## Progress\n### Software\n- [x] Get OpenCV/SimpleCV working on computer\n- [x] Develope simple \"action tracking\"\n- [x] Develope simple servo control on raspberry pi\n- [x] Add \"smooth action tracking\"\n- [x] Get OpenCV/SimpleCV working on raspberry pi\n- [x] Merge action tracking with servo control\n- [x] Optimise action finding code to run faster \n- [x] Add concurrency between servo control and action detection using [python processes](https://docs.python.org/2/library/multiprocessing.html)\n\n### Hardware\n- [x] Source tri-pod\n- [x] Mount servo to tri-pod\n- [x] Mount camera to tri-pod\n- [x] Mount Pi to tri-pod\n- [x] Mount Power to tri-pod\n- [x] 3D model case\n- [x] wire up power splitter\n\n### Extra Software\n- [x] Load via new sd card\n- [x] Add script auto-run with switch\n- [ ] Get Pi to act as wifi base\n- [ ] Connect android to Pi by wifi\n- [ ] View image from camera on android via wifi\n\n### Other processes\n- [x] Collect training data\n- [x] Build tool to help label training data\n- [x] Label training data\n\n### Notes\n\nUse `sudo modprobe bcm2835-v4l2` to activate camera.\n\n### Resources\n\nhttp://www.raspberrypi-spy.co.uk/2015/02/how-to-autorun-a-python-script-on-raspberry-pi-boot/\n\nhttps://gpiozero.readthedocs.io/en/stable/recipes.html\n\nhttps://en.wikipedia.org/wiki/Optical_flow\n\nhttp://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html\n\nhttps://www.modmypi.com/blog/how-do-i-power-my-raspberry-pi\n\nhttps://en.wikipedia.org/wiki/Recurrent_neural_network\n\n### Testing \n- [ ] Compare feature engineering with prediction speed and accuracy\n- [ ] Compare temporal framing sizes with prediction speed and accuracy\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzackakil%2Frobo-videographer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzackakil%2Frobo-videographer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzackakil%2Frobo-videographer/lists"}