If by “easy” you mean someone else already spent 5 years and a nice chunk of cash training a model for it, which you get to use. And if you accept that it will not be accurate across all possible species and environments, only very specific subsets.
I’m waiting for the day Google Recaptcha will ask me “is that traffic light red?” and after a couple of seconds “hurry up, I’m approaching the intersection!”
Do you remember what the original was?
I think it’s https://xkcd.com/1425/
*yippies in image processing degree
Funny, now it’s easy to check for birds.
If by “easy” you mean someone else already spent 5 years and a nice chunk of cash training a model for it, which you get to use. And if you accept that it will not be accurate across all possible species and environments, only very specific subsets.
You’re right, but you could say the same about the National Park GIS lookup.
also fooled by drawings and if it’s shit enough the model will be fooled by text saying “bird”
We spent the five years training the model. Manually. With Captcha data.
Now we’re teaching it not to run traffic signals, hit motorcycles or busses, or try to drive up stairs.
But if my tesla cant go how will hit those last few pedestrian
I’m waiting for the day Google Recaptcha will ask me “is that traffic light red?” and after a couple of seconds “hurry up, I’m approaching the intersection!”
https://xkcd.com/1897/
A bit of reverse image searching reveals this was the original XKCD comic (more specifically, the top middle panel): https://xkcd.com/1269/
This is original work. The source is in the post.
For a generous definition of “original”.
Edit: very generous, since it’s just new text on the second panel in https://xkcd.com/1269/
deleted by creator