Can the Jetson Orin Nano do this?

Good morning all,

I have a need to track about 20 objects in real time (30 frames per second) from a video stream. The video resolution needs to be at minimum, 1920 x 1080. Each object that will be tracked with have a unique Black letter/number on a white background. The size of that letter/number in pixels will be 45 pixels X 45 pixels which is very readable by the human eye.

I would like to stick with Python if at all possible.

I suspect this is outside the world of Raspberry Pi, or even a mini-PC.
Perhaps the Nvidia Orin Nano can do this but not sure?

Being new to this outside of basic object detection with OpenCV, I am not sure that the best process is.

Thoughts, opinions, suggestions, anything to help would be greatly appreciated.



Are the 20 objects contained in the same 1920x1080 frame?
If yes, this should be a detection problem with 20 classes.

You can find some examples below:


Yes, all objects are in the same frame and thank you for the links!