Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Community Manager
323 Views

From a novice can anyone say what the bottle necks for real time video inference?

OK, I have been playing with almost every sample that was included with a Pi 3B+ and

 

2 Movidius compute sticks. My basic question is, how do you get better performance?

 

According to the CPU monitor the PI cpu is barely taxed.

 

Its at 18 to 20%. So what changes can be made to get you the most bang for your inference buck.

 

Another board with USB3 like the ODroid XU4? Or maybe the Intel Up Board?

 

Maybe a different model? Maybe image size?

 

I am currently running at 640x480 but think 1/2HD 960x540 would deliver better edges.

 

Is it because I am using Python? Is there a guide to Movidius 30fps inference?

 

Also notice how this person is walking and not being detected. Is that because of the physical size?

 

https://ibb.co/gKdSf8

 

So far I have been able to track up to 30ft away with no real issue.
0 Kudos
0 Replies