state-of-the art computer/machine vision system
-
My answer will be simple: artificial intelligence is still nowhere.
YvesDaoust wrote:
My answer will be simple: artificial intelligence is still nowhere.
i can't fully agree with you, look at chess, can you beat a computer at it's highest skill level, i don't think so! the problem with machines of today is that they just lack perceptual skills or what is called sensory perception, they are given buttons for people to push rather than a complex sensing device. And the belief among humans that there is no such a thing as artificial intelligence discourages researchers. Remember people in the old days thought that people will never fly but we have very heavy man-made machines called planes that can fly. all we need is a break through especially in machine perception to have everybodies jaw dropped.
-
I rather meant that, having claimed that you were going to create a state of the art system that would beat anything currently available, you are now saying that you cannot do it because of the difficulty of getting a patent. That sounds like an excuse not a reason.
Unrequited desire is character building. OriginalGriff
Richard MacCutchan wrote:
I rather meant that, having claimed that you were going to create a state of the art system that would beat anything currently available, you are now saying that you cannot do it because of the difficulty of getting a patent. That sounds like an excuse not a reason.
okey lets forget about the patent issues for now, i was initually worried about ideas being stolen, but right now as i write this i'am sitting in front of a lap-top with a vision-library (designed and coded by me) capable of out-performing the current state of the art vision systems. (i'am just optimizing the library and doing some final toughes)
-
Richard MacCutchan wrote:
I rather meant that, having claimed that you were going to create a state of the art system that would beat anything currently available, you are now saying that you cannot do it because of the difficulty of getting a patent. That sounds like an excuse not a reason.
okey lets forget about the patent issues for now, i was initually worried about ideas being stolen, but right now as i write this i'am sitting in front of a lap-top with a vision-library (designed and coded by me) capable of out-performing the current state of the art vision systems. (i'am just optimizing the library and doing some final toughes)
BCDXBOX360 wrote:
i'am sitting in front of a lap-top with a vision-library (designed and coded by me) capable of out-performing the current state of the art vision systems.
In that case I'll go back to my first comment: "Let us see it in action and then we can judge.".
Unrequited desire is character building. OriginalGriff
-
mikemarquard wrote:
objects look radically different from different views. Without some sort of 3d perception it is going to be difficult to get the system to recognize multiple views as being part of the same object.
that's why my system uses a multi-view representation as i explained earlier,during the learning phase multi-views of the same object are learned and efficiently encoded for fast retrieval, this is supported in biological vision, neurons called view-tuned-units can only respond to a single view of a given 3d object but a collection of them gives a view-invariant behaviour. my system also implements a knowledge transfer technique for one-short learning (this reduces training sets as the system learns more and more things, just like humans!) and animals/humans can see effectively with a single eye proving that depth adds very little information(maybe little enough to be ignored for now). we see in what i call false 3d (it's only out of experience with this world that enables the brain to encode multi-views of various objects and cheats us that we see in 3d) the truth of the matter is that we see in 2d representation especially for recognition purposes. i think depth is used to tell how far the recognized object is from your eyes more accurately but this information is not used in actual recognition of the object.
BCDXBOX360 wrote:
my system also implements a knowledge transfer technique for one-short learning (this reduces training sets as the system learns more and more things, just like humans!) and animals/humans can see effectively with a single eye proving that depth adds very little information(maybe little enough to be ignored for now)
Actually its been found that if a person is born blind in one eye they never develop proper depth perception. The reason you and I can see in 3D if we cover an eye is because as children we learned other ques for judging depth. However, we needed 2 eyes to learn these ques because without them we have very little information to accurately gauge where an object is at and thus know how other ques corresponds to a particular location. I would say this; I don't know of any animal that has only 1 eye so I think depth perception must be important and parallax shift or I think the proper term is stereopsis is important. PS If you were the person who downvoted me I'm not trying to be critical or discourage you, I just enjoy debating these topics with people of similar interest and hearing their opinions.
-
YvesDaoust wrote:
My answer will be simple: artificial intelligence is still nowhere.
i can't fully agree with you, look at chess, can you beat a computer at it's highest skill level, i don't think so! the problem with machines of today is that they just lack perceptual skills or what is called sensory perception, they are given buttons for people to push rather than a complex sensing device. And the belief among humans that there is no such a thing as artificial intelligence discourages researchers. Remember people in the old days thought that people will never fly but we have very heavy man-made machines called planes that can fly. all we need is a break through especially in machine perception to have everybodies jaw dropped.
BCDXBOX360 wrote:
i can't fully agree with you, look at chess, can you beat a computer at it's highest skill level, i don't think so!
That's only cause computers can look at millions or even billions of times as many moves as a human can. It's actual understanding of the game is extremely weak. Look at some other games where brute force methods are less practical. Go and Arimaa are good examples. There was even a million dollar prize offered if anyone could write a good Go program by the year 2000 and nobody collected it http://senseis.xmp.net/?IngPrize[^] and there is currently a prize for Arimaa http://arimaa.com/arimaa/[^] IBM's watson was much more impressive http://www.youtube.com/results?search_query=watson&aq=f[^] but even it is only a souped up search engine, it doesn't really understand the words it's talking about it just looks at how words are used together.
BCDXBOX360 wrote:
the problem with machines of today is that they just lack perceptual skills or what is called sensory perception
I totally agree with you. True AI will never happen till the AI actually understands the meaning of the words it is talking about.
-
BCDXBOX360 wrote:
i'am sitting in front of a lap-top with a vision-library (designed and coded by me) capable of out-performing the current state of the art vision systems.
In that case I'll go back to my first comment: "Let us see it in action and then we can judge.".
Unrequited desire is character building. OriginalGriff
Richard MacCutchan wrote:
In that case I'll go back to my first comment: "Let us see it in action and then we can judge.".
okey i will make a video presentation as soon as i finish optimizing the library
-
BCDXBOX360 wrote:
my system also implements a knowledge transfer technique for one-short learning (this reduces training sets as the system learns more and more things, just like humans!) and animals/humans can see effectively with a single eye proving that depth adds very little information(maybe little enough to be ignored for now)
Actually its been found that if a person is born blind in one eye they never develop proper depth perception. The reason you and I can see in 3D if we cover an eye is because as children we learned other ques for judging depth. However, we needed 2 eyes to learn these ques because without them we have very little information to accurately gauge where an object is at and thus know how other ques corresponds to a particular location. I would say this; I don't know of any animal that has only 1 eye so I think depth perception must be important and parallax shift or I think the proper term is stereopsis is important. PS If you were the person who downvoted me I'm not trying to be critical or discourage you, I just enjoy debating these topics with people of similar interest and hearing their opinions.
mikemarquard wrote:
Actually its been found that if a person is born blind in one eye they never develop proper depth perception
But they can recognize objects effectively,right? my main interest is recognition, the question is how much does depth perception affect recognition of objects? well i do know of 3d face recognition being more accurate than the 2d counterparts but this requires 3d sensing putting a strain on cpu's. and what about all the 2d images and videos available, how will your 3d system make use of them?
mikemarquard wrote:
The reason you and I can see in 3D if we cover an eye is because as children we learned other ques for judging depth
Thank you, because thats my solution, my system learns those ques during the learning phase by presenting multi-view training sets like i wrote earlier.
mikemarquard wrote:
PS If you were t\he person who downvoted me I'm not trying to be critical or discourage you, I just enjoy debating these topics with people of similar interest and hearing their opinions.
Don't worry i'm not like that, i also enjoy discussing with people of similar interest, besides there are'nt many daredevil's to go down this path, it's gud to always hear from people like you. i wish you luck in your endeavor.
-
BCDXBOX360 wrote:
i can't fully agree with you, look at chess, can you beat a computer at it's highest skill level, i don't think so!
That's only cause computers can look at millions or even billions of times as many moves as a human can. It's actual understanding of the game is extremely weak. Look at some other games where brute force methods are less practical. Go and Arimaa are good examples. There was even a million dollar prize offered if anyone could write a good Go program by the year 2000 and nobody collected it http://senseis.xmp.net/?IngPrize[^] and there is currently a prize for Arimaa http://arimaa.com/arimaa/[^] IBM's watson was much more impressive http://www.youtube.com/results?search_query=watson&aq=f[^] but even it is only a souped up search engine, it doesn't really understand the words it's talking about it just looks at how words are used together.
BCDXBOX360 wrote:
the problem with machines of today is that they just lack perceptual skills or what is called sensory perception
I totally agree with you. True AI will never happen till the AI actually understands the meaning of the words it is talking about.
mikemarquard wrote:
That's only cause computers can look at millions or even billions of times as many moves as a human can.
Then we definately need better solutions, i have also realised that computer processing power has increased drastically but algorithms have'nt gotten smarter but just running on powerful cpu's makes them appear smart, this is definately disappointing.
-
mikemarquard wrote:
Actually its been found that if a person is born blind in one eye they never develop proper depth perception
But they can recognize objects effectively,right? my main interest is recognition, the question is how much does depth perception affect recognition of objects? well i do know of 3d face recognition being more accurate than the 2d counterparts but this requires 3d sensing putting a strain on cpu's. and what about all the 2d images and videos available, how will your 3d system make use of them?
mikemarquard wrote:
The reason you and I can see in 3D if we cover an eye is because as children we learned other ques for judging depth
Thank you, because thats my solution, my system learns those ques during the learning phase by presenting multi-view training sets like i wrote earlier.
mikemarquard wrote:
PS If you were t\he person who downvoted me I'm not trying to be critical or discourage you, I just enjoy debating these topics with people of similar interest and hearing their opinions.
Don't worry i'm not like that, i also enjoy discussing with people of similar interest, besides there are'nt many daredevil's to go down this path, it's gud to always hear from people like you. i wish you luck in your endeavor.
BCDXBOX360 wrote:
But they can recognize objects effectively,right? my main interest is recognition, the question is how much does depth perception affect recognition of objects? well i do know of 3d face recognition being more accurate than the 2d counterparts but this requires 3d sensing putting a strain on cpu's. and what about all the 2d images and videos available, how will your 3d system make use of them?
I would assume yes because I've never seen anything written on that subject. So you are probably right that it is possible, but I still suspected it will learn faster with 3D.
BCDXBOX360 wrote:
mikemarquard wrote:
The reason you and I can see in 3D if we cover an eye is because as children we
learned other ques for judging depthThank you, because thats my solution, my system learns those ques during the learning phase by presenting multi-view training sets like i wrote earlier.
Yeah but that's the point I was making earlier. Without some preexisting method for judging distances you have nothing to use as a measuring stick when your system would learn those cues. That's why people born blind in one eye don't learn those cues, because they cannot use stereopsis as a measuring stick. They have no way to see how things like for instance the size of an object corresponds with it's distance from the viewer because they never actually know how far the object is from them.
BCDXBOX360 wrote:
Don't worry i'm not like that, i also enjoy discussing with people of similar interest, besides there are'nt many daredevil's to go down this path, it's gud to always hear from people like you. i wish you luck in your endeavor.
Thanks
-
BCDXBOX360 wrote:
But they can recognize objects effectively,right? my main interest is recognition, the question is how much does depth perception affect recognition of objects? well i do know of 3d face recognition being more accurate than the 2d counterparts but this requires 3d sensing putting a strain on cpu's. and what about all the 2d images and videos available, how will your 3d system make use of them?
I would assume yes because I've never seen anything written on that subject. So you are probably right that it is possible, but I still suspected it will learn faster with 3D.
BCDXBOX360 wrote:
mikemarquard wrote:
The reason you and I can see in 3D if we cover an eye is because as children we
learned other ques for judging depthThank you, because thats my solution, my system learns those ques during the learning phase by presenting multi-view training sets like i wrote earlier.
Yeah but that's the point I was making earlier. Without some preexisting method for judging distances you have nothing to use as a measuring stick when your system would learn those cues. That's why people born blind in one eye don't learn those cues, because they cannot use stereopsis as a measuring stick. They have no way to see how things like for instance the size of an object corresponds with it's distance from the viewer because they never actually know how far the object is from them.
BCDXBOX360 wrote:
Don't worry i'm not like that, i also enjoy discussing with people of similar interest, besides there are'nt many daredevil's to go down this path, it's gud to always hear from people like you. i wish you luck in your endeavor.
Thanks
mikemarquard wrote:
So you are probably right that it is possible, but I still suspected it will learn faster with 3D.
According to wikipedia "Stereopsis appears to be processed in the visual cortex in binocular cells having receptive fields in different horizontal positions in the two eyes. Such a cell is active only when its preferred stimulus is in the correct position in the left eye and in the correct position in the right eye, making it a disparity detector." you are right 3d vision is useful, i will consider using two cameras,but i will start with a single camera then move to 3d implementation this will enable my system to take advantage of both worlds, thanks for the advice. I thought through this and realised that i left stereopsis out but now i have considered using it, i have found that there is room for it in my vision system, i do'nt have to modify the whole library but just add additional functions to support stereopsis, thanks again for stereopsis.
-
Hi, i'am a researcher in computer vision system (Electronics Engineer by profession) designing a system capable of out performing the current state of the art vision system. OpenCV 2.2 did not impress me, vision by machines seems 2 lag behind the simplest animal u can think of (like a cat or something else). i think computers are powerful enough 2 handle vision nearly as good as humans. Why are the state of art vision systems very task specific and not as robust as they should be?any suggestions?
To help keep your ground-breaking revolutionary work at the fever-pitch required to personally transcend several centuries of person-years' work on computer vision ... I think you need a good moniker, a rallying cry ... a logophone ... May I suggest: GrandEyeOsity. best, Bill
"Last year I went fishing with Salvador Dali. He was using a dotted line. He caught every other fish." Steven Wright
-
To help keep your ground-breaking revolutionary work at the fever-pitch required to personally transcend several centuries of person-years' work on computer vision ... I think you need a good moniker, a rallying cry ... a logophone ... May I suggest: GrandEyeOsity. best, Bill
"Last year I went fishing with Salvador Dali. He was using a dotted line. He caught every other fish." Steven Wright
BillWoodruff wrote:
To help keep your ground-breaking revolutionary work at the fever-pitch required to personally transcend several centuries of person-years' work on computer vision ...
I think you need a good moniker, a rallying cry ... a logophone ...
May I suggest: GrandEyeOsity.
best, BillIt happens to be that "GrandEyeOsity" also sounds like "Grandiosity" which is not a good moniker,and by stating that i have designed a computer-vision system capable of out-performing current state of the art systems does'nt mean i did not re-use some of the earlier ideas, you should know that i did not have to re-invent the wheel, but to look at what the other researchers have missed-out or overlooked which happens to be ground-breaking. If you are a true developer, you should be able to understand what research and development means. What others have failed to achieve, i have managed, simple as that and no nicknames please!
-
BillWoodruff wrote:
To help keep your ground-breaking revolutionary work at the fever-pitch required to personally transcend several centuries of person-years' work on computer vision ...
I think you need a good moniker, a rallying cry ... a logophone ...
May I suggest: GrandEyeOsity.
best, BillIt happens to be that "GrandEyeOsity" also sounds like "Grandiosity" which is not a good moniker,and by stating that i have designed a computer-vision system capable of out-performing current state of the art systems does'nt mean i did not re-use some of the earlier ideas, you should know that i did not have to re-invent the wheel, but to look at what the other researchers have missed-out or overlooked which happens to be ground-breaking. If you are a true developer, you should be able to understand what research and development means. What others have failed to achieve, i have managed, simple as that and no nicknames please!
I sincerely wish you all the best in your Quest, Sir Knight ! And, when the "Grail of Vision" thing is done, I'll be happy to grant Thee the boon of being your Squire-Errant ... ... if you provide me with a donkey to ride named "El Rucio," and you ride a knight-worthy-nag whose name must be "Rocinante" ... to accompany you on the Quest for the "recognition of sense of humor." Windmills ahoy ! :) best, Bill
"Last year I went fishing with Salvador Dali. He was using a dotted line. He caught every other fish." Steven Wright
-
BillWoodruff wrote:
To help keep your ground-breaking revolutionary work at the fever-pitch required to personally transcend several centuries of person-years' work on computer vision ...
I think you need a good moniker, a rallying cry ... a logophone ...
May I suggest: GrandEyeOsity.
best, BillIt happens to be that "GrandEyeOsity" also sounds like "Grandiosity" which is not a good moniker,and by stating that i have designed a computer-vision system capable of out-performing current state of the art systems does'nt mean i did not re-use some of the earlier ideas, you should know that i did not have to re-invent the wheel, but to look at what the other researchers have missed-out or overlooked which happens to be ground-breaking. If you are a true developer, you should be able to understand what research and development means. What others have failed to achieve, i have managed, simple as that and no nicknames please!
You talk the talk, but can you walk the walk?
Unrequited desire is character building. OriginalGriff I'm sitting here giving you a standing ovation - Len Goodman
-
Hi, i'am a researcher in computer vision system (Electronics Engineer by profession) designing a system capable of out performing the current state of the art vision system. OpenCV 2.2 did not impress me, vision by machines seems 2 lag behind the simplest animal u can think of (like a cat or something else). i think computers are powerful enough 2 handle vision nearly as good as humans. Why are the state of art vision systems very task specific and not as robust as they should be?any suggestions?
BCDXBOX360 wrote:
vision by machines seems 2 lag behind the simplest animal u can think of (like a cat or something else).
:confused: I doubt that a cat qualifies as the simplest animal I can think of; besides, if they had such a simple visual system, they wouldn't probably be the formidable predators that they are....
-
BCDXBOX360 wrote:
vision by machines seems 2 lag behind the simplest animal u can think of (like a cat or something else).
:confused: I doubt that a cat qualifies as the simplest animal I can think of; besides, if they had such a simple visual system, they wouldn't probably be the formidable predators that they are....
sgorozco wrote:
I doubt that a cat qualifies as the simplest animal I can think of; besides, if they had such a simple visual system, they wouldn't probably be the formidable predators that they are....
You are right cats are not the simplest animals. But "simple" in this context is a relative measure (let's say relative to computer/machine vision potential) and that computers of today are capable of running a vision system advanced enough to make a cat look like a cockroach but no such vision system exists because there are'nt many efforts to do that as many people like doing the easy stuff.
-
To help keep your ground-breaking revolutionary work at the fever-pitch required to personally transcend several centuries of person-years' work on computer vision ... I think you need a good moniker, a rallying cry ... a logophone ... May I suggest: GrandEyeOsity. best, Bill
"Last year I went fishing with Salvador Dali. He was using a dotted line. He caught every other fish." Steven Wright
Have you seen the computer vision system I have developed? check here http://www.youtube.com/watch?v=euHMcUfqpVo[^] :laugh:
“Everything is simple when you take your time to analyze it.”
-
You talk the talk, but can you walk the walk?
Unrequited desire is character building. OriginalGriff I'm sitting here giving you a standing ovation - Len Goodman
See the stuff I was talking about, I walk the talk, http://www.youtube.com/watch?v=euHMcUfqpVo[^] :laugh:
“Everything is simple when you take your time to analyze it.”
-
It sounds like your ideas and my ideas are a lot different. Actually my ideas ideas are a lot different than any of the ideas I've read about and my image segmentation is technically not an edge detection algorithm either. I wish you the best of luck and if you have some big successes I'd love to hear about it.
BCDXBOX360 wrote:
- My system is not currently designed to use stereo cameras it uses a single camera and does not need depth or capturing a 3D representation to aid recognition.
You might have more limited aims than I do but I have to question this one. If you're trying to build something that is capable of doing what a human or animal can do I don't see how this can work cause clearly humans and animals see in 3d. Also if you choose this path keep in mind objects look radically different from different views. Without some sort of 3d perception it is going to be difficult to get the system to recognize multiple views as being part of the same object.
Check out the system I have developed from ground up here, http://www.youtube.com/watch?v=euHMcUfqpVo[^] :)
“Everything is simple when you take your time to analyze it.”