preller/test-pose

1---2title: MediaPipe Pose Detection API3emoji: 🏃4colorFrom: blue5colorTo: purple6sdk: docker7app_port: 80008python_version: 3.119pinned: false10license: apache-2.011app_file: main.py12short_description: Process videos with MediaPipe pose detection13tags:14  - mediapipe15  - computer-vision16  - pose-detection17  - fastapi18---19 20# MediaPipe Pose Detection API21 22This Hugging Face Space provides an API for processing videos with MediaPipe's pose detection model. Upload your video and get back a processed version with pose landmarks drawn on it.23 24## API Usage25 26### Process a Video27```28POST /process-video/29```30 31Upload a video file and receive a processed video with pose landmarks.32 33Example using curl:34```bash35curl -X POST -F "file=@your_video.mp4" https://your-space-name.hf.space/process-video/ --output processed_video.mp436```37 38## How it Works39 40The application:411. Receives an uploaded video file422. Extracts frames from the video433. Processes each frame with MediaPipe's pose detection444. Draws the pose landmarks on each frame455. Combines the processed frames into a new video466. Returns the processed video47 48## Technical Details49 50- Uses MediaPipe for efficient pose detection51- Built with FastAPI for high-performance API endpoints52- Optimized for processing large videos with batch processing and memory management53