Markerless tracking and pose estimation

Hello everyone,

We’re in the process of developing a web application that displays an MJPEG stream. Our goal is to identify specific objects in the video in real-time and perform pose estimation. Ideally, we’d like it to function in a way similar to fiduciary markers, but instead, leverage computer vision algorithms to enable markerless tracking.

Could anyone share insights on whether this is feasible using OpenCV.js?

the js version is cute, but it only contains a subset of opencv features
(and it seems terribly hard to add new features)

so, difficult decision, unless you have a full concept, & can check detailsc …