AI 姿态估计

使用基于浏览器的 AI 从图片中估计人体姿态

所有处理均在浏览器中完成,不会上传任何数据。
Offline Ready
File Input
Camera

Pose Estimation

Detect body pose (33 landmarks) in an image with MediaPipe PoseLandmarker, running entirely in your browser. The model downloads once on first use; nothing is uploaded.

🔒所有处理均在浏览器中完成,不会上传任何数据。