Hi,
I am trying to implement pose estimation in C++ to detect and infer data simultaneously from two USB webcams (with the same resolution and FPS). However, the code is quite tricky, and I am not sure how to approach it.
I think that establishing a correspondence between webcams and frames and processing them simultaneously with Hailo could be a good option, but I am not sure how to implement it. Is this the most optimized way to do it?
I started with the basic C++ code from the Hailo repository on Raspberry Pi 5 with Hailo-8L and yolov8s_pose.hef, and I want to integrate it with that code:
Any advice or guidance would be greatly appreciated!
Thanks a lot, it looks quite interesting, but everything is in Python, and I need C++. I think the complexity of that application is much higher than what I need, which is simply analyzing two video sources simultaneously with yolov8_pose.hef for pose estimation and obtaining only the YOLO outputs, without any need for visualization. I was looking for a quick integration, possibly with a multithreaded process already implemented in C++.