{"id":51644337,"url":"https://github.com/lewdry/mac-track","last_synced_at":"2026-07-13T21:02:43.934Z","repository":{"id":359979194,"uuid":"1244695461","full_name":"lewdry/mac-track","owner":"lewdry","description":"Experiment with computer vision. opencv, MediaPipe, Yolov8 and emoji.","archived":false,"fork":false,"pushed_at":"2026-06-24T12:45:15.000Z","size":25082,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-24T14:18:55.283Z","etag":null,"topics":["mediapipe","opencv","yolov8"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lewdry.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-20T14:03:25.000Z","updated_at":"2026-06-24T12:45:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/lewdry/mac-track","commit_stats":null,"previous_names":["lewdry/mac-track"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/lewdry/mac-track","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewdry%2Fmac-track","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewdry%2Fmac-track/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewdry%2Fmac-track/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewdry%2Fmac-track/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lewdry","download_url":"https://codeload.github.com/lewdry/mac-track/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewdry%2Fmac-track/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35436281,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-13T02:00:06.543Z","response_time":119,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["mediapipe","opencv","yolov8"],"created_at":"2026-07-13T21:02:42.626Z","updated_at":"2026-07-13T21:02:43.924Z","avatar_url":"https://github.com/lewdry.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Mac Track — Computer Vision Lab\n\nLocal object detection for Apple Silicon (M1/M2/M3) Macs using MediaPipe and YOLOv8 via OpenCV.\n\n\u003cimg width=\"600\" height=\"336\" alt=\"Screen Recording 2026-05-20 at 11 16 46 pm (1)-dithered\" src=\"https://github.com/user-attachments/assets/04ca8f22-891f-4c4f-b3cd-225704721fa9\" /\u003e\n\n\u003cimg width=\"600\" height=\"338\" alt=\"emojihead_recording_1780020619-dithered\" src=\"https://github.com/user-attachments/assets/3a6e5637-a0a5-4fd9-a3de-72f0ece79f8f\" /\u003e\n\n\u003cimg width=\"600\" height=\"338\" alt=\"processed_VID_20170916_173146-dithered\" src=\"https://github.com/user-attachments/assets/0c954ade-89a2-46d8-91f5-d5be2fc299c9\" /\u003e\n\n\u003cimg width=\"600\" height=\"643\" alt=\"processed_c82053f1-b511-4ef2-94ac-4463c16a3956-dithered\" src=\"https://github.com/user-attachments/assets/d552cb58-d94b-4d50-9306-cfaa55a24363\" /\u003e\n\n## Setup\n\nOpen a terminal, navigate to your project folder, and run:\n\n```bash\npython3 -m venv venv\nsource venv/bin/activate\npip install --upgrade pip\npip install opencv-python mediapipe ultralytics\n```\n\nThen download the MediaPipe EfficientDet model:\n\n```bash\ncurl -L -o efficientdet.tflite \"https://storage.googleapis.com/mediapipe-models/object_detector/efficientdet_lite0/int8/1/efficientdet_lite0.tflite\"\n```\n\n## Scripts\n\n| Script | Description |\n|---|---|\n| `yolo.py` | YOLOv8 object detection on your webcam, GPU-accelerated on Apple Silicon. Supports photo and video capture. |\n| `yololive.py` | Live webcam feed with ghostly/glitchy pose and object detection overlays. |\n| `yolopost.py` | Batch processes all videos in `input/`, adds object and pose overlays, and saves results to `output/`. |\n| `pose.py` | Real-time human pose (skeleton) tracking via MediaPipe. |\n| `poseobj.py` | Real-time multi-object tracking via MediaPipe. |\n| `emojihead.py` | Overlays an emoji on up to four detected faces in your webcam feed. |\n\n## Examples - Running\n\n**MediaPipe** — lightweight CPU pipeline using Google's Tasks API:\n```bash\npython poseobj.py\n\nor \n\npython emojihead.py\n```\n\n**YOLOv8** — high-accuracy detection accelerated on Apple Silicon GPU via Metal Performance Shaders:\n```bash\npython yolo.py\n\nor \n\npython yololive.py\n```\n\n## Keyboard Controls\n\n| Key | Action |\n|---|---|\n| `SPACE` | Capture a PNG snapshot with tracking boxes |\n| `r` | Start / stop video recording |\n| `q` | Quit and close all windows |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flewdry%2Fmac-track","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flewdry%2Fmac-track","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flewdry%2Fmac-track/lists"}