Tag
A developer built an AI basketball coach using Roboflow RF-DETR for detection, MediaPipe for body angles, and OpenCV for analysis and annotation.
A girl used Claude AI and free software TouchDesigner and MediaPipe to develop a real-time interactive system for controlling 3D objects with hand gestures at extremely low cost, and successfully commercialized it, charging $5,000–$15,000 per event.
Vision Agents is an open-source Python framework for building multimodal AI agents that process video and audio in real time. It enables conversational agents to adapt their voice based on facial expressions and gaze using MediaPipe.