search

AndreyGermanov / yolov8_onnx_rust

YOLOv8 inference using Rust
GNU General Public License v3.0
51 stars 7 forks source link

Can we add webcam as a input for inference? #2

Closed nawinrajkumar closed 11 months ago

nawinrajkumar commented 11 months ago

Can we add a webcam as input using Videocapture? It would be very useful for deploying the code on Edge Devices as Rust has high inference rate. @AndreyGermanov

AndreyGermanov commented 11 months ago

Thanks for your interest!

The idea is great, but it goes out of scope of this repository, because this code related to the article, that already published.

So, this could be a great idea for a new project: to get video from a webcam in the browser and then send video frames to the Rust-backend for inference.

I already wrote article about web browser part here: https://dev.to/andreygermanov/how-to-detect-objects-in-videos-in-a-web-browser-using-yolov8-neural-network-and-javascript-lfb. You can use frontend code from that article to get video frames from the web-camera, and then combine it with Rust code from this repository to implement inference of those frames on the backend.