houmo-ai/mediapipe_plus

The purpose of this project is to apply mediapipe to more AI chips.

44
/ 100
Emerging

This project helps integrate Google MediaPipe's computer vision capabilities into a wider range of AI hardware, specifically Nvidia's Jetson AGX Xavier. It takes an input video and processes it with AI models, such as a face detection model, to produce an output video with detections (like facial bounding boxes and landmarks). This is primarily used by embedded systems developers or AI hardware engineers who need to deploy high-performance computer vision applications on edge devices.

Use this if you are an embedded systems developer working with Nvidia Jetson AGX Xavier and need to accelerate MediaPipe-based computer vision inference using TensorRT for faster, more efficient edge AI applications.

Not ideal if you are an end-user without a technical background in AI hardware, embedded systems, or C++/Bazel development, as this project requires significant technical setup and coding knowledge.

Embedded AI Edge Computing Computer Vision Deployment AI Hardware Acceleration Real-time Video Processing
No License No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

53

Forks

16

Language

C++

License

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/houmo-ai/mediapipe_plus"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.