OAKI is your personal trainer that tries to do the training in home more fun and with metrics to find if you are doing a good exercise. It combines mediaPipe algorithms, depth from the OAKD-lite, functions to find angles and distances between points, some multiprocess to run everything in parallel, and an assistant voice to have a fantastic experience in training.
Install libraries necessary for the project
pip install -r requirements.txt
Run this command to start the app.
python app.py
As our application grows we would refactor our app.py file into multiple folders and files.
.
├── app.py
├── oakiAgent.py
├── .gitignore
├── requirements.txt
├── README.md
├── voice
| ├── 0.mp4
| ├── 1.mp4
| ├── 2.mp4
| ├── 3.mp4
| ├── 4.mp4
| ├── 5.mp4
| ├── 6.mp4
| ├── 7.mp4
| ├── 8.mp4
| ├── 9.mp4
| ├── 10.mp4
| ├── 11.mp4
| └── 12.mp4
├── methods
| ├── body_part_angle.py
| ├── types_of_exercise.py
| └── utils.py
└── imgMention the tools you used to create your project
- OpenCV - OpenCV provides a real-time optimized Computer Vision library, tools, and hardware
- MediaPipe - MediaPipe offers cross-platform, customizable ML solutions for live and streaming media.
- DepthAI - DepthAI is the embedded spatial AI platform built around Myriad X
- NVIDIA GTX960M - Run in RealTime
- OAKD-Lite - Depth Camera
We use SemVer for versioning. For all available versions, see whattags in this repository.
- Adonai Vera - Member DS4a - AdonaiVera
You can also look at the list of all contributors who have participated in this project.
This project is under the License, see the file LICENSE.md more details.
- Tell others about this project 📢
- Give thanks publicly 🤓.