Vehicle Recognition and Counting

I’m looking to use the Wyze Pan Cam as an informal traffic counter - I have the camera set up to view the street, and would like to be able to 1/ differentiate between vehicles and people (I have AI recognition turned on), and 2/ try to automate the vehicle count. Any way to do this currently?

1 Like

Currently, no. I agree it would be super cool to be able to set up smarter custom AI on an individual basis, but I’m not really sure what would that would entail and what would be possible. Realistically, I think it’s probably unlikely to happen, because it would probably be tough to make it very user-friendly, but if it were possible, it would certainly be a game-changer. To the extent that it’s possible, I think it would involve a lot of trial and error and patience, at least. I posted a similar “wish” in this thread.

Vehicle detection was originally rolled out in beta when person detection was for original testing. it would make sense to me that they’re going to use person testing and get all the issues ironed out in that first before they re-release vehicle detection if they decide to. But the software is there somewhere :slight_smile:

I would like “anything man-size or larger” detection. If an elephant, lion, bear, ape, car, truck or human enters my domain, I would like to know. I will have to take my chances of not being robbed be short people.

Yep, good call, I just saw Godzilla King of the Monsters.

I just don’t know what I would do if an elephant, lion, bear or ape came to my house?

1 Like

I like that idea, but without a 3D camera, it’s probably easier said than done, for this reason:

Ok - that makes sense. Hope that the AI is opened up to allow user generated tags that would facilitate the vehicle recognition! Thanks for all the feedback.

I agree, it would be awesome. Even if we get vehicle recognition, or custom recognition based on AI, (which I wouldn’t expect for a long time, if ever – although it would be amazing!) vehicle counting is probably even a step beyond that.

1 Like