Best sensor IR for counting cigarette butts

Hi again @Virgil,

Yes, you can use the Pixy2 camera or any other camera module or image sensor for that matter. The great thing about this module is that it integrates a powerful processor that runs the tracking/following algorithms so your microcontroller doesn’t have to process all the information and you don’t have to program these algorithms. It also has a great frame rate (60 fps), which means that you get a complete update of all detected objects’ positions every 16.7 ms. At this rate, tracking the path of a falling object is possible (A ball traveling at 40 mph moves less than a foot in 16.7 ms). Also as the Pixy2 uses a hue-based color filtering algorithm to detect objects, the object needs to have a distinct hue. The good thing is that cigarette butts have an orange/yellow hue so it would be great if the background is black or white. You can find more information about the Pixy2 here, about object tracking here and this may also be relevant to you.

I’ve played around with the Pixy1Cam a while and want to add, that it works best under controlled ilumination. (always same brightness and such)
With cigarette butts, which can have some odd shapes, you might see multiple counts. But there are a few parameters to deal with that.

Hi @geraldinebc15
Alright, thanks for your response, so I’ll try all of this and keep you posted!

1 Like

hi @o_lampe
Okay ! I will test it all then!