KemanIT
Posts: 1
Joined: Tue Oct 01, 2019 11:37 am

video analysis from IP camera

Tue Oct 01, 2019 11:45 am

Good morning, I write to get information from someone more experienced than me.

I'm trying to create a facial recognition system using the Open CV library, but I need to know if it is possible to do a video stream analysis of an online IP camera and not a physically compatible one with raspberry.

look for answers,
Thanks in advance

User avatar
topguy
Posts: 5908
Joined: Tue Oct 09, 2012 11:46 am
Location: Trondheim, Norway

Re: video analysis from IP camera

Thu Oct 03, 2019 11:33 pm

In theory yes.. in practice it depends on your IP camera.

https://stackoverflow.com/questions/499 ... hon-opencv

User avatar
jbeale
Posts: 3500
Joined: Tue Nov 22, 2011 11:51 pm
Contact: Website

Re: video analysis from IP camera

Fri Oct 04, 2019 2:09 am

There are posted examples of facial recognition using the Raspberry Pi, for example https://www.pyimagesearch.com/2018/06/2 ... cognition/

don't expect it to work very fast, as this needs a lot of computation. He mentions 1 or 2 FPS for face recognition, but you can get 8 or 10 fps if you're just doing tracking, or face detection instead of specific individual recognition.

There are "AI accelerator" add-on USB devices that can speed up specific kinds of deep learning networks by a factor of maybe 10x on the Pi. Not sure if they would be specifically applicable to this task or not.

Coral from Google: https://coral.withgoogle.com/products/accelerator/
Neural Compute Stick 2 from Intel: https://www.amazon.com/Intel-Neural-Com ... 07KT6361R/

Return to “Graphics, sound and multimedia”