News for hackers. Stuff that matters.
Re:This AI Boom Will Also Bust by dTal on Saturday December 03, 2016 @01:53PM (#13096915)
Stereo vision is obviously highly effective in biology as it has independently evolved a great many times. Time-of-flight may be poised for a renaissance, but it scales badly and is active, not passive. Stereo vision, and its big brother light fields, are far more general and are certainly not going to "die out".
Re:This AI Boom Will Also Bust by sangnoir on Saturday December 03, 2016 @03:52PM (#13097442)
> Stereo vision is obviously highly effective in biology as it has independently evolved a great many times

This argument sounds like a second cousin of the "chemicals are bad, but if it is natural it is good" argument. Just because it evolved in nature doesn't mean it's optimal, or it's the best system under massively different constraints. And who knows what evolution would have thrown up after a few more billion years.

Re:This AI Boom Will Also Bust by aangjie on Sunday December 04, 2016 @09:07AM (#13100012)
I think the point he was making is that it is effective in different environmental challenges and constraints. Not that it's optimal. So it might still be useful for building into a robot that's supposed to explore a environment(think space and planets for example). It may get relegated to academia, if we find other optimal solutions for our robots doing our boring chores though.
Re:This AI Boom Will Also Bust by eli_gottlieb on Saturday December 03, 2016 @05:41PM (#13097850)
Human vision is active rather than passive as well. We really wouldn't be able to get around the world if we relied on passive inference from sensory stimuli to model our environment.
Re:This AI Boom Will Also Bust by revelation on Saturday December 03, 2016 @02:04PM (#13096969)
Yet humans produce terrible depth data.
Re:This AI Boom Will Also Bust by kd0amg on Saturday December 03, 2016 @03:05PM (#13097267)
Terrible for what purpose? Humans seem pretty good at throwing things to each other and catching them. I'm very bad at coming up with a good numeric estimate of linear size. As a fencer, I could never tell you how many inches between me and my opponent, how long his or my arms are, how tall he is, etc. I could definitely tell you which parts of our bodies are within reach of each other's arm extension, fleche, lunge, etc.
Re:This AI Boom Will Also Bust by michaelt on Saturday December 03, 2016 @06:35PM (#13098027)
Terrible for the purpose of proving a general-purpose stereo machine vision system is practical.

The distance at which a stereo vision system can capture precise depths depends on the distance between eyes, and the eyes' angular resolution. Human depth perception works well for things within about 10m, but when you get out to 20-40m humans get a lot less info from stereo vision.

When you get to that distance, humans seem to have a whole load of different tricks - shadows, rate of size change, recognising things of known size, perspective and so on. You can see a car and know how far it is even without stereo vision, because you know how big cars are, and how big lanes and road markings are. You can even see two red lights in the distance at night and work out whether they're the two corners of a car, or two motorbikes side-by-side and closer to you.

On the other hand, your basic general-purpose stereo machine vision system doesn't try to understand what it's looking at - you just identify 'landmarks' that can be matched in both images (high contrast features, corners etc) and measure the difference in angle from the two cameras. This is relatively simple and easy to understand!

For tasks that humans can do that involve depth perception of things more than ~40m away - flying a plane, for example, where most things are more than 40m away if you're doing it right! - nice simple stereo vision can't get the job done, because humans are actually using their other tricks.

Of course, despite this limitation stereo vision comes up a lot in nature - it's still a beneficial adaption, because most things in nature that will kill you do so from less than 10m away :)

Re:This AI Boom Will Also Bust by matt_kantor on Saturday December 03, 2016 @10:33PM (#13098664)
> Of course, despite this limitation stereo vision comes up a lot in nature - it's still a beneficial adaption, because most things in nature that will kill you do so from less than 10m away :)

It's actually pretty rare for non-predatory animals to have good stereo vision. Most of them are optimized for a wide field of view instead, evolving eyes placed on either side of their head. Think rabbits, parrots, bison, trout, iguanas, etc.

https://en.wikipedia.org/wiki/Binocular_vision

https://www.quora.com/Why-have-most-animals-evolved-to-see-o...

Re:This AI Boom Will Also Bust by taneq on Sunday December 04, 2016 @09:05AM (#13100010)
It depends what you mean by "practical", though. If you mean "practical for use as a dense 3D reconstruction technique" then sure, it's pretty bad. If you mean "usable under an incredible range of lighting conditions and situations" then I'd say it's practical.

Edit: IMO binocular vision is probably more to do with redundancy than depth perception. If you damage or lose an eye, you can still operate at near full capacity. Losing vision 'in the wild' is a death sentence.

Re:This AI Boom Will Also Bust by jonathankoren on Saturday December 03, 2016 @03:00PM (#13097249)
Humans produce good enough depth data.
Re:This AI Boom Will Also Bust by kgwgk on Saturday December 03, 2016 @03:03PM (#13097261)
What does it mean? I'd say the ability to perceive depth is pretty useful.
Re:This AI Boom Will Also Bust by ianai on Sunday December 04, 2016 @02:37AM (#13099182)
Actually brains eventually learn how to discern distance with one eye too, iirc.