{"id":15650562,"url":"https://github.com/cansik/mediapipe-osc","last_synced_at":"2025-04-30T17:42:30.257Z","repository":{"id":54711794,"uuid":"319599880","full_name":"cansik/mediapipe-osc","owner":"cansik","description":"MediaPipe examples which stream their detections over OSC.","archived":false,"fork":false,"pushed_at":"2022-05-16T22:00:45.000Z","size":385,"stargazers_count":43,"open_issues_count":2,"forks_count":10,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-30T18:23:06.830Z","etag":null,"topics":["computer-vision","hand-tracking","mediapipe","osc","pose-estimation"],"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/cansik.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}},"created_at":"2020-12-08T10:12:39.000Z","updated_at":"2024-12-20T21:14:02.000Z","dependencies_parsed_at":"2022-08-14T00:40:35.238Z","dependency_job_id":null,"html_url":"https://github.com/cansik/mediapipe-osc","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/cansik%2Fmediapipe-osc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cansik%2Fmediapipe-osc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cansik%2Fmediapipe-osc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cansik%2Fmediapipe-osc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cansik","download_url":"https://codeload.github.com/cansik/mediapipe-osc/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251752978,"owners_count":21638211,"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":["computer-vision","hand-tracking","mediapipe","osc","pose-estimation"],"created_at":"2024-10-03T12:35:05.950Z","updated_at":"2025-04-30T17:42:30.209Z","avatar_url":"https://github.com/cansik.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MediaPipe OSC\n[MediaPipe](https://google.github.io/mediapipe/) examples which stream their detections over OSC to be used in other applications.\n\n### Install \u0026 Run\n\nCurrently this is only tested on Windows and MacOS. It's recommended to use Python3 (`\u003e3.7`) and a virtual environment.\n\n```bash\npython install -r requirements.txt\n```\n\nTo run an example use the basic python command to start up the script.\n\n```bash\n# start pose detection with webcam 0\npython pose.py --input 0\n\n# start pose detection with video\npython pose.py --input yoga.mp4\n```\n\nOther parameters are documented in the following list or algorithm specific.\n\n- **input** - The video input path or video camera id (default `0`)\n- **min-detection-confidence** - Minimum confidence value ([0.0, 1.0]) for the detection to be considered successful. (default `0.5`)\n- **min-tracking-confidence** - Minimum confidence value ([0.0, 1.0]) to be considered tracked successfully. (default `0.5`)\n- **ip** - OSC ip address to send to (default `127.0.0.1`)\n- **port** - OSC port to send to (default `7500`)\n\n### Full-Body Pose Landmark Model (BlazePose Tracker)\nThe landmark model currently included in MediaPipe Pose predicts the location of 33 full-body landmarks (see figure below), each with (`x, y, z, visibility`). Note that the z value should be discarded as the model is currently not fully trained to predict depth, but this is something we have on the roadmap.\n\n![Pose Description](readme/pose_tracking_full_body_landmarks.png)\n\n*[Reference: mediapipe/solutions/pose](https://google.github.io/mediapipe/solutions/pose#pose-landmark-model-blazepose-tracker)*\n\n**Additional Parameters**\n\n```\n--model-complexity MODEL_COMPLEXITY\n                      Set model complexity (0=Light, 1=Full, 2=Heavy).\n--no-smooth-landmarks\n                      Disable landmark smoothing.\n--static-image-mode   Enables static image mode.\n```\n\n#### Format\n\n- `count` - Indicates how many poses are detected (currently only `0` or `1`)\n- list of landmarks (`33` per pose) (if pose has been detected)\n    - `x` - X-Position of the landmark\n    - `y` - Y-Position of the landmark\n    - `z` - Z-Position of the landmark\n    - `visibility` - Visibility of the landmark\n\n```\n/mediapipe/pose [count, x, y, z, visibility, x, y, z, visibility ...]\n```\n\n### Hand Detection\nThe [hand detection model](https://google.github.io/mediapipe/solutions/hands.html) is able to detect and track 21 3D landmarks.\n\n#### Format\n\n- `count` - Indicates how many hands are detected\n- list of landmarks (`21` per hand) (if hands has been detected)\n    - `x` - X-Position of the landmark\n    - `y` - Y-Position of the landmark\n    - `z` - Z-Position of the landmark\n    - `visibility` - Visibility of the landmark\n\n```\n/mediapipe/hands [count, x, y, z, visibility, x, y, z, visibility ...]\n```\n\n### Face Detection\nThe [face detection model](https://google.github.io/mediapipe/solutions/face_detection.html) is able to detect multiple faces and 5 keypoints. At the moment only the bounding box is sent over OSC.\n\n#### Format\nAll values are normalized to the image width and height.\n\n- `count` - Indicates how many faces are detected\n- list of one bounding box per face (if faces has been detected)\n    - `xmin` - X-Position of the top-left bounding box anchor\n    - `ymin` - Y-Position of the top-left bounding box anchor\n    - `width` - Width of the bounding box\n    - `height` - Height of the bounding box\n    - `score` - Confidence score of the bounding box\n\n```\n/mediapipe/faces [count, xmin, ymin, width, height, score, xmin, ymin, width, height, score ...]\n```\n\n### Face Mesh\ntbd\n\n### Examples\n\nCurrently, there are very basic receiver examples for processing. Check out the [examples](examples) folder.\n\n### About\n* Example code and documentation adapted from [google/mediapipe](https://google.github.io/mediapipe/solutions/)\n* OSC sending and examples implemented by [cansik](https://github.com/cansik)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcansik%2Fmediapipe-osc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcansik%2Fmediapipe-osc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcansik%2Fmediapipe-osc/lists"}