Adding Pose Classification for the Strike a Pose Demo #195
Description
Description
Enhance the Strike a Pose demo, which estimates poses of all people standing in front of the webcam, by implementing pose classification. This feature will classify different poses detected by the demo, providing more detailed insights into the types of poses individuals are making.
This project will involve Python programming; basic experience with AI models from frameworks like PyTorch, TensorFlow, OpenVINO, or ONNX is beneficial. To learn more about the OpenVINO toolkit, visit the documentation here.
Steps:
-
Implement Pose Classification:
- Develop a feature that classifies different poses detected by the demo.
- Ensure that the classification is accurate and can handle various poses.
-
Enhance User Experience:
- Add real-time labels to display the classified poses.
- Ensure the classification feature does not significantly impact the pose estimation demo's performance, maintaining results within a reasonable time frame (without significantly slowing down the current demo).
-
Documentation:
- Add to the documentation with clear and detailed instructions for setting up and running the enhanced demo.
- Include comments in the code to explain key sections and logic.
How to Get Started:
- Fork the OpenVINO Build Deploy repository.
- Follow these installation instructions to setup your environment and install the required dependencies for this project.
- Read Demo Contribution Guide.
- Build your feature and ensure it meets the requirements specified in the contribution guide.
- Submit a pull request.