{"id":23715675,"url":"https://github.com/jshulgach/hand-landmark-tracker","last_synced_at":"2025-10-09T15:33:55.271Z","repository":{"id":189200473,"uuid":"678063555","full_name":"Jshulgach/Hand-Landmark-Tracker","owner":"Jshulgach","description":"An app created with PyQt5 using Google's MediaPipe hand landmark ML model for hand tracking and streaming","archived":false,"fork":false,"pushed_at":"2025-06-14T00:18:12.000Z","size":75890,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-09T15:33:25.044Z","etag":null,"topics":["computer-vision","hand-tracking","machine-learning","mediapipe","opencv","pyqt5","python"],"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/Jshulgach.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}},"created_at":"2023-08-13T15:09:16.000Z","updated_at":"2025-06-14T00:18:16.000Z","dependencies_parsed_at":"2025-04-05T06:32:48.960Z","dependency_job_id":null,"html_url":"https://github.com/Jshulgach/Hand-Landmark-Tracker","commit_stats":{"total_commits":4,"total_committers":2,"mean_commits":2.0,"dds":0.5,"last_synced_commit":"583944bc4d55f1fbb0e606e1064867d886227020"},"previous_names":["jshulgach/hand-landmark-tracker"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Jshulgach/Hand-Landmark-Tracker","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jshulgach%2FHand-Landmark-Tracker","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jshulgach%2FHand-Landmark-Tracker/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jshulgach%2FHand-Landmark-Tracker/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jshulgach%2FHand-Landmark-Tracker/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Jshulgach","download_url":"https://codeload.github.com/Jshulgach/Hand-Landmark-Tracker/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jshulgach%2FHand-Landmark-Tracker/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279001645,"owners_count":26083147,"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","status":"online","status_checked_at":"2025-10-09T02:00:07.460Z","response_time":59,"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":["computer-vision","hand-tracking","machine-learning","mediapipe","opencv","pyqt5","python"],"created_at":"2024-12-30T20:59:32.283Z","updated_at":"2025-10-09T15:33:55.256Z","avatar_url":"https://github.com/Jshulgach.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/hand-demo.gif\" width=\"70%\"\u003e\n\u003c/div\u003e\n\n\u003c!-- ![](assets/hand-demo.gif) --\u003e\n\n# Hand Landmark Tracker \u0026nbsp;[![](https://img.shields.io/badge/python-3.8.5-blue.svg)](https://www.python.org/downloads/)\nHand Landmark Tracker bring a new perspective to human-computer interaction using hands. The hand is the most versatile and intuitive controller someone can use, so it makes sense to see if there is a way to design an interface that takes advantage of the hands without requiring them to touch anything.\nThis code uses the amazing features of Google's machine learning suite [MediaPipe](https://developers.google.com/mediapipe), a media-based ML package for classification and recognition with neural networks.\n\n\u003c!-- This program uses openCV and mediapipe to acquire hand landmarks and post/gesture tracking commands to stream to a [Robot Web Server]().  --\u003e\n\n\u003c!-- \u003cfigure\u003e --\u003e\n\u003c!--  \u003cimg src=\"./assets/hand-demo.gif\" alt=\"Hand\" width=\"500\" height=\"400\"\u003e\u003cbr\u003e --\u003e\n\u003c!--  \u003cfigcaption\u003eLandmark tracking. Multi-hand classification and landmark identification.\u003c/figcaption\u003e --\u003e\n\u003c!-- \u003c/figure\u003e --\u003e\n\n## Installation\n\n1. Create a virtual environment using [Anaconda](https://www.anaconda.com/products/distribution) or Python's virtualenv.\n   - Using Anaconda:\n      ~~~\n      conda create -n hand-tracker python=3.8\n      conda activate hand-tracker\n      ~~~\n   - Using Python's virtualenv:\n     ~~~\n     python3 -m venv hand-tracker\n     source hand-tracker/bin/activate # Linux\n     call hand-tracker/Scripts/activate # Windows\n     ~~~\n2. Clone the repository and navigate to the project directory.\n   ~~~\n   git clone https://github.com/Jshulgach/Hand-Landmark-Tracker.git\n   cd Hand-Landmark-Tracker\n   ~~~\n3. Install the required packages.\n    ~~~\n    pip install -r requirements.txt\n    ~~~\n\n\n## Getting Started\n\n### Hand tracker Class\nThe HandTracker class can be easily imported and used in your own projects by creating an instance of the class and calling the `track` method.\n```python\nfrom tracking import HandTracker\ntracker = HandTracker(visualize=True) # Enable visualization on a CV frame\ntracker.run()\n```\nThis will start hand tracking and displaying any landmarks captured on top of detected hands.\n\n\u003c!-- ![](assets/handtracker-landmarks.png) --\u003e\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/handtracker-landmarks.png\" width=\"70%\"\u003e\n\u003c/div\u003e\n\n### MiniArm Gripper Virtual Spacemouse Control\n\nA more interesting demo is using hand tracking like a virtual spacemouse as a position displacement controller operating the position of a robot end effector. We can use the [MiniArm](https://github.com/Jshulgach/Mini-Arm) robot for example and send position and gripper commands to the robot server.\n\nTo run the spacemouse demo, the `main.py` script can be run with the `spacemouse` mode and COM port set. Enabling the verbose mode allows for text output of the tracking data.\n~~~\npython main.py --mode spacemouse --port COM5 --verbose true\n~~~\n\n\u003c!-- ![](assets/robot-grasping-gui-trim.gif) --\u003e\n\u003c!-- ![](assets/gripper-crop-trim.gif) --\u003e\n\u003cdiv align=\"right\"\u003e\n  \u003cimg src=\"assets/robot-grasping-gui-trim.gif\" width=\"50%\"\u003e\n\u003c/div\u003e\n\u003cdiv align=\"left\"\u003e\n  \u003cimg src=\"assets/gripper-crop-trim.gif\" width=\"50%\"\u003e\n\u003c/div\u003e\n\n\n## Acknowledgement\n\nThe project was inspired by xenon-19's [Gesture Controlled Virtual Mouse](https://github.com/xenon-19/Gesture-Controlled-Virtual-Mouse) project.\n Thanks Google for the amazing [MediaPipe](https://developers.google.com/mediapipe) library.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjshulgach%2Fhand-landmark-tracker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjshulgach%2Fhand-landmark-tracker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjshulgach%2Fhand-landmark-tracker/lists"}