{"id":24576116,"url":"https://github.com/jennnital/tdmultifacetracking","last_synced_at":"2026-02-25T12:02:09.967Z","repository":{"id":272908589,"uuid":"916622070","full_name":"jennnital/TDMultiFaceTracking","owner":"jennnital","description":"Real-time Multi-face Tracking in TouchDesigner with OpenCV \u0026 YuNet","archived":false,"fork":false,"pushed_at":"2025-02-15T12:08:41.000Z","size":4342,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-15T12:28:07.384Z","etag":null,"topics":["face-tracking","opencv","real-time","touchdesigner","touchdesigner-tools","yunet"],"latest_commit_sha":null,"homepage":"https://github.com/jennnital/TDMultiFaceTracking","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/jennnital.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}},"created_at":"2025-01-14T13:11:13.000Z","updated_at":"2025-02-15T12:08:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"2086b17a-c80a-4b70-b9cc-175208cda191","html_url":"https://github.com/jennnital/TDMultiFaceTracking","commit_stats":null,"previous_names":["jennnital/fforfragile"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jennnital%2FTDMultiFaceTracking","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jennnital%2FTDMultiFaceTracking/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jennnital%2FTDMultiFaceTracking/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jennnital%2FTDMultiFaceTracking/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jennnital","download_url":"https://codeload.github.com/jennnital/TDMultiFaceTracking/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244036141,"owners_count":20387461,"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":["face-tracking","opencv","real-time","touchdesigner","touchdesigner-tools","yunet"],"created_at":"2025-01-23T22:21:30.392Z","updated_at":"2026-02-25T12:02:04.935Z","avatar_url":"https://github.com/jennnital.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TouchDesigner Multi-face Tracking with OpenCV and YuNet\n\n## Overview  \nThis repository provides implementations for multi-face tracking in TouchDesigner using two methods:  \n- **YuNet**: A deep learning-based face detection model.  \n- **OpenCV Cascade Classifier**: A traditional method using Haar cascades.  \n\n---\n\n## YuNet  \nIn the folder `face_detection_yunet`, you will find the TouchDesigner implementation of YuNet.\n\n### Video Source  \n- This example uses `op('VideoSource')` as the source for face detection.  \n- To test with your own video, replace the file path in the operator.  \n\n### Model Setup  \n- In `DAT script2_callbacks`, update the system path to the `face_detection_yunet` folder on **line 6**.  \n- Path format is `r\"C:\\....` for Windows.  \n\n### Hardware Acceleration  \n- This implementation attempts to use **CUDA** if OpenCV DNN CUDA support is available.  \n- If CUDA is not found, it will automatically switch to **CPU** processing.  \n\n---\n\n## OpenCV  \nThe folder `OpenCV` contains an implementation using the **Cascade Classifier** from OpenCV in TouchDesigner.  \n\n### Features  \n- This example detects faces and applies a blur effect on them.  \n\n---\n\n## Requirements  \n- TouchDesigner  \n- OpenCV with DNN module support (for YuNet)  \n- CUDA (optional, for hardware acceleration)  \n\n---\n\n## Installation  \n1. Clone this repository:  \n    ```bash\n    git clone https://github.com/yourusername/TD-Multi-face-Tracking.git\n    ```\n2. Install required Python packages:  \n    ```bash\n    pip install opencv-python opencv-python-headless\n    ```\n3. Update system paths in the scripts as mentioned above.  \n\n---\n\n## Usage  \n1. Open the corresponding TouchDesigner project file.  \n2. Adjust video source paths as needed.  \n3. Run the project and observe real-time face tracking.  \n\n---\n\n## License  \nThis project is licensed under the MIT License.  \n\n---\n\n## Acknowledgments  \n- [OpenCV](https://opencv.org/)  \n- [YuNet Face Detection Model](https://github.com/opencv/opencv_zoo)  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjennnital%2Ftdmultifacetracking","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjennnital%2Ftdmultifacetracking","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjennnital%2Ftdmultifacetracking/lists"}