Flowy is an AI-powered yoga instructor that enhances your yoga practice by analyzing your poses in real time and providing personalized suggestions for improvement. For each pose, it assigns a score based on the accuracy of your execution, using three precision levels - 10, 50 or 100 - which represent the percentage of pose accuracy.
Elevate your yoga with AI guidance!
Starting from the brief ‘Things That Think’, we began our design process with an idea generation session, collecting all concepts on individual post-its. Most of the ideas revolved around using machine learning (ML) tools to detect and interpret visual input through a camera. This led us to focus on the idea of recognizing user poses during various activities, eventually narrowing it down to yoga poses.
With this foundation, we conceptualized an object designed to assist individuals practicing yoga at home while offering real-time feedback. We envisioned a compact device that could function either as a smartphone accessory (app + phone stand) or as a standalone unit with its own screen. In both cases, portability was key, ensuring users could enjoy yoga sessions wherever they are.
Next, we explored the technologies that could support our goal. After experimenting with different tools and ML models (e.g., Teachable Machine, LLAVA), we discovered that GPT-4o was the most effective for our needs. During this phase, we also considered integrating skeleton detection with MediaPipe to enhance feedback accuracy. However, GPT-4o proved highly reliable in correctly identifying yoga poses.
The primary input is the front-facing camera, which tracks the user’s movements. The outputs include both visual elements (such as a timer, pose illustration and performance score) and auditory feedback to guide the user in real-time.
In the following images, you can see how we trained an LLM to recognize various yoga poses and subsequently perfected them through the use of code.
