Hello GestureCap mentors,
My name is Pranav Ghorpade. I am a student of Electronics and Telecommunication Engineering and a potential GSoC contributor of 2025.
I am very interested in the GestureCap project and I have already implemented a working prototype that matches the objectives of the project. The current system includes:
Markerless hand and full-body pose tracking using MediaPipe
Gesture-based sound generation with non-blocking audio
- End-to-end latency measurement (~ 25-35 ms)
- Gesture debouncing and stability handling
- Quantitative latency logging for evaluation
Repository: https: / / github. com / Pranav-0440 / gesturecap-demo
(Readme includes architecture and demo details)
I created this prototype to better understand the requirements of GestureCap and to serve as an extensible baseline for expressive music and speech production, agency analysis, and user studies.
Thank you very much for any comments on the following:
- Is this approach consistent with the direction of this year’s project?
- Which extensions will be most valuable to focus on before the proposal phase.
Thank you for your time and I look forward to your guidance.
Greetings,
Pranav Ghorpade