MediaPipe Holistic Landmarker

Note

“Text-to-Speech” is jointly developed by RTKSG SD3 and ChungYi Fu (Kaohsiung, Taiwan)

Special thanks and credits to the efforts and contributions for all developers.

Materials

• AMB82-mini x 1

Example

In this example, we will be using development board to stream JPEG using HTTP and apply MediaPipe Holistic Landmarker on the streaming page.

Open MediaPipe Holistic Landmarker example in File -> Examples -> AmebaNN -> MultimediaAI -> MediaPipe_Holistic_Landmarker

In the highlighted code snippet fill in the “ssid” with your WiFi network SSID and “pass” with the network password.

Compile and upload the example.

Open the serial monitor to view the logs.

Please copy the IP address for “Main page” printed on the log and paste it on your browser to view the stream.

Resources

MediaPipe Holistic Overview

https://github.com/google-ai-edge/mediapipe/blob/master/docs/solutions/holistic.md

MediaPipe Tasks Vision Package

https://www.jsdelivr.com/package/npm/@mediapipe/tasks-vision