Trapper/Hunter's camera

asked 2017-11-17 18:37:38 -0500

sjhalayka gravatar image

updated 2017-11-18 15:38:16 -0500

A guy and I are designing a trapper/hunter's camera, something that you can strap onto a tree. It's mostly for fun... we'll likely never make it to the production phase.

If motion is detected, the camera starts recording to file. But, you don't want to record the background branches swaying in the breeze.

What method would you use to differentiate between recorded and non-recorded frames of video?

I was thinking of using an artificial neural network, where the training data is gotten from a forced recording. Another method would be to get the large contour areas in the motion detection (ie. difference) frame.

Whatever it turns out to be, it will be open source, and the user is free to alter it as they see fit.

edit retag flag offensive close merge delete

Comments

1

You have raspberry pi 3 and picamera?

supra56 gravatar imagesupra56 ( 2017-11-19 20:18:20 -0500 )edit

No, but from the looks of it, I should. Thanks! Is this camera good enough? --> https://www.canakit.com/raspberry-pi-...

Are they controllable using C++?

sjhalayka gravatar imagesjhalayka ( 2017-11-19 20:27:32 -0500 )edit
1

Absolutely. You can use pizero instead of raspberry pi 3. Yes, you can do in c++.

supra56 gravatar imagesupra56 ( 2017-11-20 03:48:59 -0500 )edit

Thanks again!

sjhalayka gravatar imagesjhalayka ( 2017-11-20 15:27:41 -0500 )edit