Hacker News Reader

Comment by aab0 | Hacker News Reader

How necessary is the deep model there? It seems like a simple motion detector would work just as well since he doesn't mention using the lawn himself.

View on HN

Semantic segmentation/FCN isn't necessary since the spray isn't targeting the cat location specifically - you could just use a whole image classifier. You don't need a TX1 either, you could run this on a spare phone

https://www.tensorflow.org/mobile.html

http://mxnet.readthedocs.io/en/latest/how_to/smart_device.ht...

https://github.com/jetpacapp/DeepBeliefSDK

This could certainly be done well sans deep model, but a motion detector alone would probably end up soaking the occasional delivery guy / neighborhood kid.

Looks like there is a sidewalk through the lawn. Which probably means using a motion detector would force him to sacrifice using the front door.

You could either:

1) set the motion detection area only on the lawn 2) Set a delay for like > 30s movement 3) Set times of movement (ie. when they're at work)

But the big question is: did it work ?

If you create any kind of safe path in such a system, the cat will learn it quickly too.

One simpler way to go IMO would be to put the system at ground level and use two motion detectors, one aimed specifically to "see" only things that are a meter or more above the ground. Humans would trigger both, but the cat would only trigger the one aimed at the ground.

See, the advantage with that plan is that even if the cats figure out how to bypass that system, now you can assuage the pain of failure by filming the cats leaping across your yard like pogo sticks and monetize the video on YouTube. Tens of millions of views guaranteed.

Yeah this guy needs to read more. Anything that could perform a simple matrix multiplication could be used.

Reply on news.ycombinator.com