Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ComputerVisionWiki.org

computervisionwiki.org

Post reply on HN
Print view View original

11–20 of 22 posts

Re: ComputerVisionWiki.org

#11

Post by pixcavator »

mnemonicsloth wrote: post #9
ecuzzillo wrote: post #6

Earlier quoted context omitted.

It doesn't work in the sense everybody most wants it to work, which is to slap a cheap CCD camera or three on top of a mobile robot and have it tell the robot everything about its surroundings, like human vision can. Yeah, if you point a camera at a very restricted specific set of objects, all lit the same way, and all in generally the same basic configuration, you can do some vaguely useful statistics to get some in…

It's interesting -- I started writing this exact definition of "works" in my post above. Anthropomorphic bias, right? Even with this understanding, though, I can't wrap my brain around what you're saying above. Computer vision doesn't "work" (for our definition of "work") because it's not feasible to get enough processing power together: O( 3e10 ) neurons * 100 Hz/neuron = more cycles than you can rent on an NSF gran…

Yes, it is a bias. I think it is a big mistake to try to solve the problem by emulating how humans see because we don't know how humans see (here's a rant of mine on a related topic http://inperc.com/blog2/2007/10/12/%e2%80%9cbrain-inspired%e...).

Re: ComputerVisionWiki.org

#12

Post by ecuzzillo »

mnemonicsloth wrote: post #9
ecuzzillo wrote: post #6

Earlier quoted context omitted.

It doesn't work in the sense everybody most wants it to work, which is to slap a cheap CCD camera or three on top of a mobile robot and have it tell the robot everything about its surroundings, like human vision can. Yeah, if you point a camera at a very restricted specific set of objects, all lit the same way, and all in generally the same basic configuration, you can do some vaguely useful statistics to get some in…

It's interesting -- I started writing this exact definition of "works" in my post above. Anthropomorphic bias, right? Even with this understanding, though, I can't wrap my brain around what you're saying above. Computer vision doesn't "work" (for our definition of "work") because it's not feasible to get enough processing power together: O( 3e10 ) neurons * 100 Hz/neuron = more cycles than you can rent on an NSF gran…

I don't think we're doing that much processing to do vision. It's never the case that even close to all the cells in the visual cortex are being used. It's always a tiny fraction of that. Yeah, we have a bunch of cells that neuroscientists think are somehow related to doing vision, but there's no evidence that they're doing some kind of horribly computationally intensive thing all day long. If they were, we'd see it on MRI's as soon as we put a picture in front of somebody.

No, I think we just haven't figured out what to do, not that we're limited by computational resources. I think there are a bunch of pretty strong assumptions hardwired into the brain, so we can see physical objects, but then you can fool us by showing us images that mess with the assumptions (aka optical illusions).

(Not that this is a particularly useful idea, mind you. I'm not about to solve computer vision. It's just a random philosophical idea.)

Re: ComputerVisionWiki.org

#13

Post by mnemonicsloth »

ecuzzillo wrote: post #12
mnemonicsloth wrote: post #9

Earlier quoted context omitted.

It's interesting -- I started writing this exact definition of "works" in my post above. Anthropomorphic bias, right? Even with this understanding, though, I can't wrap my brain around what you're saying above. Computer vision doesn't "work" (for our definition of "work") because it's not feasible to get enough processing power together: O( 3e10 ) neurons * 100 Hz/neuron = more cycles than you can rent on an NSF gran…

I don't think we're doing that much processing to do vision. It's never the case that even close to all the cells in the visual cortex are being used. It's always a tiny fraction of that. Yeah, we have a bunch of cells that neuroscientists think are somehow related to doing vision, but there's no evidence that they're doing some kind of horribly computationally intensive thing all day long. If they were, we'd see it…

It's never the case that even close to all the cells in the visual cortex are being used. It's always a tiny fraction of that.

This is also true of any individual transistor in a processor. An ALU contains hardware to perform many operations, but at most performs one per cycle. You can increase utilization through parallelism and pipelining, but you pay for it with more synchronization and control hardware that only switches on to resolve conflicts. And nowadays, half of all the transistors in a CPU are part of a cache (every cycle, you need a word or two, but get the whole block). You can't conclude that they're not making a contribution to output from the fact that they're often inactive.

No, I think we just haven't figured out what to do, not that we're limited by computational resources.

Based on what evidence? We know that the brain is hugely complex. We know it can sort through hugely complex problem spaces at least some of the time. Doesn't it seem like wishful thinking to assume both that the brain is really inefficient and that most of the problems it solves actually have simple hueristic solutions?

I'll step up and take ownership of the end result of this argument: If what you say is true and understanding is all we lack, why have these problems proved so stubborn?

Re: ComputerVisionWiki.org

#14

Post by ed »

If anyone is considering building apps in this area, I'd strongly suggest checking out OpenCV.

It's _far_ more powerful than Pixcavator, well supported, liberally licensed, and provides some really awesome high-level API's.

Re: ComputerVisionWiki.org

#15

Post by pixcavator »

mnemonicsloth wrote: post #13
ecuzzillo wrote: post #12

Earlier quoted context omitted.

I don't think we're doing that much processing to do vision. It's never the case that even close to all the cells in the visual cortex are being used. It's always a tiny fraction of that. Yeah, we have a bunch of cells that neuroscientists think are somehow related to doing vision, but there's no evidence that they're doing some kind of horribly computationally intensive thing all day long. If they were, we'd see it…

It's never the case that even close to all the cells in the visual cortex are being used. It's always a tiny fraction of that. This is also true of any individual transistor in a processor. An ALU contains hardware to perform many operations, but at most performs one per cycle. You can increase utilization through parallelism and pipelining, but you pay for it with more synchronization and control hardware that only…

>If what you say is true and understanding is all we lack, why have these problems proved so stubborn?

Understanding is hard, why is this so surprising?

Re: ComputerVisionWiki.org

#16

Post by ivankirigin »

ecuzzillo wrote: post #4
bluishgreen wrote: post #2

Could any one suggest a good book on Vision. Something like Cormen for algorithms.

The reason there isn't a definitive text on vision is that vision doesn't work. Algorithms work, and so to have a definitive text, you just collect up all the notable ones that work, and write about them in a book. When you have a totally unsolved problem like vision (outside of certain highly constrained domains, like robot soccer, where the colors are guaranteed, or industrial tasks, where basically the whole scene…

Saying that "vision doesn't work" is like saying "audio doesn't work". Outside a particular problem, you can't generalize to that level.

Automated surveillance from a fixed camera works extremely well (VSAM). Certain object class recognition like face or pedestrian detection works extremely well (Viola & Jones). Stereo depth extraction, some systems with amazing & cheap custom ASICs, works extremely well (Tyzx). 2D object instance recognition works extremely well (SIFT). This can power SLAM when combined with stereo imagery. Object Tracking works extremely well (Collins). Traversable road classification, car detection, road boundary & lane detection, and Stereo/SFM will power the first semi-autonomous cars. All that tech works really well today -- the task is system integration.

Also, vision isn't just visible light cameras. ASC is making a flash lidar that would make you drool. The "Swiss Ranger" is also good. Both can provide snap-shot volumetric 3D data combined with color and texture information, with no moving parts. They'll scale much better than scanning lidars and even multi-laser systems like Velodyne.

Add 3D processing like Spin Images to the mix, and integrated vision systems will get very, very powerful, very soon.

I like AnyBot's approach, but I think it is incorrect to assume "AI" won't be good enough and tele-operation will be king. If I were a pure-software robotics startup, I would focus on vision & navigation software, large/networked system integration/configuration/scalability utilities (like I'm sure you're building), and behavior systems.

For a text, I would recommend reading the winning papers from major vision/machine learning/robotics conferences, and the papers they reference. Grad students at CMU's Robotics Institute use Forsyth & Ponce's "computer vision, a modern approach". http://www.amazon.com/Computer-Vision-Approach-David-Forsyth...

I would also recommend Mitchell's "Machine Learning", Strang's "Linear Algebra and it's applications", and throw in Thrun's new "Probabilistic Robotics" for fun.

Re: ComputerVisionWiki.org

#17

Post by plinkplonk »

bluishgreen wrote: post #2

Could any one suggest a good book on Vision. Something like Cormen for algorithms.

This (http://www.amazon.com/Introductory-Techniques-3-D-Computer-V...) is the best book on Computer Vision I 've come across. I first encountered it when trawling Stanford courses for good problem sets and research projects. Sebastian Thrun used to teach a class with this book (http://robots.stanford.edu/cs223b04/). It is fairly expensive and fairly mathematical but it is worth every cent you pay for it (imho).

Good Luck !

Re: ComputerVisionWiki.org

#18

Post by pixcavator »

ed wrote: post #14

If anyone is considering building apps in this area, I'd strongly suggest checking out OpenCV. It's _far_ more powerful than Pixcavator, well supported, liberally licensed, and provides some really awesome high-level API's.

If you know what 'the Laplacian of the Gaussian' is, definitely go for OpenCV. If you'd like to see something based on high school math, try this wiki.

Re: ComputerVisionWiki.org

#19

Post by mnemonicsloth »

pixcavator wrote: post #15
mnemonicsloth wrote: post #13

Earlier quoted context omitted.

It's never the case that even close to all the cells in the visual cortex are being used. It's always a tiny fraction of that. This is also true of any individual transistor in a processor. An ALU contains hardware to perform many operations, but at most performs one per cycle. You can increase utilization through parallelism and pipelining, but you pay for it with more synchronization and control hardware that only…

>If what you say is true and understanding is all we lack, why have these problems proved so stubborn? Understanding is hard, why is this so surprising?

Because understanding is almost always easier than data collection and tool-building.

Pure lack of understanding -- having all the data and having no idea what it means -- can keep a problem open for a generation or two. Einstein is famous because he solved a problem in EM physics that was at most 30 years old.

Lack of data or meaningful investigative techniques can keep a subject crippled for centuries. Physics went from rolling marbles to detecting radio waves in the two hundred fifty years since Galileo, while biology was pretty much stagnant. Without organic chemistry, even scientists were willing to believe that living organisms were made of some special God-stuff. Contrast that to the last 20 years. The human genome has been sequenced by biologists on their way to designing new organisms while physicists have been stuck throwing models around since the 1970s. Petri dishes are cheaper than supercolliders.

Now let's look at AI and machine vision. Our primary tools, brain imaging and computer simulation, are getting better every year. Maybe new ideas in algorithms or parallel architecture will bring "real" computer vision closer. In fact, they probably will. But even if they don't, this approach will definitely succeed eventually:

http://news.bbc.co.uk/2/hi/technology/6600965.stm

Re: ComputerVisionWiki.org

#20

Post by pixcavator »

mnemonicsloth wrote: post #19
pixcavator wrote: post #15

Earlier quoted context omitted.

>If what you say is true and understanding is all we lack, why have these problems proved so stubborn? Understanding is hard, why is this so surprising?

Because understanding is almost always easier than data collection and tool-building. Pure lack of understanding -- having all the data and having no idea what it means -- can keep a problem open for a generation or two. Einstein is famous because he solved a problem in EM physics that was at most 30 years old. Lack of data or meaningful investigative techniques can keep a subject crippled for centuries. Physics went…

I don't have as many examples but here is one. Galileo discovered his principle by conducting very simple experiments with no special tools or a lot of data collection. How do you find the relevant data or build relevant tools if you don't have a clue about what you are supposed to discover?

What computer vision needs is mathematics, in my opinion. And math has nothing to do with "data collection and tool-building". It is entirely about understanding.

The link provides a good example of how people try to solve problems without any understanding. They don't know how the brain operates, yet they build its "model". And then they expect this model to solve the problem for them...

Post reply on HN