Slashdot Mirror
Hands-On With Microsoft's Touchless SDK
snydeq writes "Fatal Exception's Neil McAllister takes Microsoft's recently released Touchless SDK for a test spin, controlling his Asus Eee PC 901 with a Roma tomato. The Touchless SDK is a set of .Net components that can be used to simulate the gestural interfaces of devices like the iPhone in thin air — using an ordinary USB Webcam. Although McAllister was able to draw, scroll, and play a rudimentary game with his tomato, the SDK still has some kinks to work out. 'For starters, its marker-location algorithm is very much keyed to color,' he writes. 'That's probably an efficient way to identify contrasting shapes, but color response varies by camera and is heavily influenced by ambient light conditions.' Moreover, the detection routine soaked up 64 percent of McAllister's 1.6GHz Atom CPU, with the video from the Webcam soon developing a few seconds' lag that made controlling onscreen cursors challenging. Project developer Mike Wasserman offers a video demo of the technology."
the SDK still has some kinks to work out.
Sure sounds like it.
Is this why they have cameras built into the digital TV converter boxes?
-=/\- Jizzbug -/\=-
Can it recognise that someone's about to pick up a chair?
Sounds a lot like the stuff developers have been doing with the Eyetoy since PS2... I wonder if this tech will show up on the 360, and they're just getting the kinks out now with this stuff? I don't know if people would use that practically since they would have to switch from having their hands up in the air to down on the keyboard/mouse for various things... Maybe it can be used for kiosks for people who worry about germs...
Twinstiq, game news
.
You really don't expect efficient code from Microsoft, do you?
While it's very vogueish to make comparisons with Apple products lately, Sony's Cambridge studio are the group that spring to mind when it comes to gestural webcam-based interfaces. On a related note, their original Eyetoy tech demos were similarly "keyed to color", using large foam props, although the end product worked on skintones and therefore was heavily dependent on good lighting and contrast. They patented a "wand" with coloured LEDs back in 2005 which provided a reasonable compromise between the two (a month or two before the Wii Controller popped up, and made it all look passe).
No kidding!!! What do you say at this point?
he's your new fucking god.
Maybe I'm parsing this incorrectly, but you seem to have a somewhat unique insight into his abilities in bed.
No kidding!!! What do you say at this point?
You know, someone should have really told these guys about this thing called a low-pass filter. It's very easily implemented in hardware (heck, most DSPs can do it rather handily), and uses very little power. A TI dsp would have no problem handling this kind of load.
As for mediocre hardware, yes, the EEE is a little underpowered compared to a desktop. But, when you consider the fact that a 200 MHz dsp can encode NTSC video in realtime, chewing up 60% of the CPU is just poor implementation. That's ~1 GHz on a fully pipelined, superscalar processor, with a heatsink, to do what an embedded DSP can do with oh, say about 50-100 MHz of processing power, without a heatsink, using a RISC processor, running on AA batteries.
And this yet one of the reasons I believe programmers should have to learn hardware. They wouldn't write code so inefficiently if they only understood the typical hardware engineer's approach to these problems.
The society for a thought-free internet welcomes you.
Running Linux. And the voice commands actually work!
I'm not sure why I'd bother to chew up my battery with the webcam when I can just talk to the thing. If anything, it seems to me like the voice recognition would be far more promising than using the webcam.
Okay, I know how this is going to sound, and I'm really not trying to troll, so please bear with me. I suppose there's a contingent of people who like the thought of waving their hands in the air to control their computer (Wii users?!), but I just don't see this going anywhere, especially because Microsoft is involved. If you look at their history, they typically get things wrong the first few times. Whatever promise this technology holds, I expect that:
The society for a thought-free internet welcomes you.
I remember reading a year ago that some Toshiba Qosmios could recognize gestures. This is not the article I read, but the first I found.
Also, I don't think it's fair to kick Microsoft over this. It seems to be a bit of an experiment. I'd love to see this on Linux though, another step closer to the Minority Report world.
Is there any reasonable person/entity that doesn't consider the MS-PL Open Source? http://www.opensource.org/licenses/ms-pl.html http://en.wikipedia.org/wiki/Shared_source#Microsoft_Public_License_.28Ms-PL.29
you're a bit late, it's been done already, but with a wii remote. http://www.cs.cmu.edu/~johnny/projects/wii/
If you're interested in a truely Open Source version of this, Pygame has camera and computer vision functions in the SVN that let you do exactly this. I could track two different colored objects in realtime (30fps) with no lag, on a 433mhz OLPC XO.
It is Linux only at the moment, but Windows and OS X support is likely to be finished before the next release.
eclecti.cc
Brown Chair Of Death. There! I coined it.
MS-PL is entirely open source and OSI-compliant, you tool.
"You can either have software quality or you can have pointer arithmetic, but you cannot have both at the same time."
Intel made a very nice open source library for computer vision. It's called OpenCV [http://sourceforge.net/projects/opencvlibrary/] and can be used to track pixels (or hands, or heads...).
I first saw it on Pycon Brasil 2008, with EHCI python bindings [http://www.slideshare.net/dannyxyz22/ehci-interao-com-computador-atravs-de-webcam-presentation].
Microsoft library is not a big deal... I made a script to switch KDE desktops using face moviments with 45 lines of python script + ehci, including a lot of useless code and testing/debuging prints. :-)
Thiago F Pappacena
openframeworks wraps c++ like processing wraps java, also has opencv bindings.
MS appears to basically doing optical flow & color tracking. the above libs can do those, and more, and are great for programmers and nonprogrammers alike. tho if you really hate code, you may rather use max/msp/jitter or gem/pd.
Was just trying to watch the video (on my desktop, Linux). It hangs terribly and there is zero sound. I don't really see the reason for this video to eat up so much resources at that qality. Is the technology it is presenting of similar superiority? Is it designed for low spec portable devices?
Reverting mod.
not that this is on topic at all but I have karma to burn. McCain may be old but he won't be having a heart attack as soon as he gets into office. If he was going to have one, hes under enough pressure just campaigning. Same goes for Obama. It's not like they're going to decrease the security he gets when he gets into office. He will be just as protected as he is now if not more so. No matter who gets elected, it is very unlikely that their VP will take over. It is good to evaluate the VP with the pres because they will reflect the values of their running mate as well. But don't assume that they will be in charge if their running mate gets elected. Your negative pessimistic attitude just reinforces itself in others and further erodes confidence in the United States of America. Secret Service won't let Obama get assassinated and McCain is not in such terrible health that he is going to have a heart attack the day he gets into office. We will probably have seen more time with Cheney in charge of the country in the end than either Palin or Biden will spend in charge.
like many other slashfags, it's apparent that you dont know jack shit about anything. go watch g4 or whatever it is you do when not wasting your time here.
Hmm, I guess I bought into the FUD. I didn't realize MS-PL was OSI approved.
Regardless, I posted a video to Youtube showing multiple object tracking on an OLPC XO.
eclecti.cc
This could be used to great effect with people that have handicaps that prevent the use of standard interfaces. Gestures that they CAN perform can be programed to take the place of gestures they cannot, ones that we all take for granted.
Microsoft has a bunch of labs/departments dedicated to just making stuff until one catches on... a bit like Google, but instead of being "everyone", its some departments. So they'll make stuff like this or DeepZoom, which may or may not catch on... others like Spec# may have more potential.
It's not the official Microsoft release. It's a home project of one (MS) programmer. But, hey, "Hands-On With Touchless SDK made by some dude who happens to work for Microsoft" isn't much of a headline, right?
.
In a financial crisis the prize goes to the last man standing
Microsoft is the first U.S. industrial corporation in ten years to earn a AAA bond rating from S&P and Moody's.
More than 70 percent of S&P ratings for U.S. nonfinancial companies are currently below investment grade and classified as "junk", or speculative-grade bonds. That's up from 32 percent in 1980. Microsoft wins top credit ratings from S&P, Moody's
You can type "killer aunt delete all" with sign language now too!
The FSF and OSI consider it open source and it's GPLv3 compatible.
That was disturbing in so. many. levels. I mean that was close to tubgirl or goatse..... if not worse.
Your evaluation period for Productivity 1.0 has ended. Please purchase more coffee to continue using this product.
First off, you sound like a marketing campaign. Second off, Microsoft didn't invent the mouse and neither did Apple. Spreadsheets were NOT created by Microsoft. USB ?!? Are you smoking crack ?!
Sorry, but you are either a troll or someone who is employed by the PR firm handling Microsoft. Vista is trash, you know it and MS knows it.
Microsoft isn't alone in this, but I do get the impression that they have a few research units that they fund as window dressing, that are constantly presenting exciting demos of pretty cool stuff that never make it into actual products and never will.
Like Detroit's "concept cars."
Or Xerox PARC's Alto.
Or a Fortune 500 company I worked at that collapsed with astonishing speed. Little groups were always coming up with amazing things, and higher-ups were always clucking admiringly over them, but the little groups never had the internal political connections to get them turned into actual products.
The actual decisions on what got made into products were based on what the salespeople that called on the bank CEOs had to say. And the bank CEOs never told the salespeople that they were ready to write $100 million dollar checks for smell navigation or a spreadsheet for calculating music or whatever.
(Probably one of the things that makes Apple what it is, for good or for bad, is that it's run by a guy who has pretty good taste in ideas and is willing to back good ideas just because he thinks they are good).
"How to Do Nothing," kids activities, back in print!
I think this is an example of how the GPU is much more suited for image analysis. I'd be very interested in exactly how this was managed on a XO! I have an 8 year old mac running at 733MHz, but it has a 9800 ATI which allows it to do real time image effects with my webcam while also only using about 60% cpu. See http://www.samkass.com/blog/page4/page4.html for some examples of what one person has done using webcams. Its using the Quartz Composer from apple developer tools. Edit: I found out about the XO: http://eclecti.cc/olpc/pixel-perfect-collision-between-real-and-virtual-objects Seems its' just really efficient code!
Once again, Microsoft takes a simple concept and finds a way to complicate it. Way to go, Redmondians!
You need to explore 'Help & Preferences' to avoid this.
This was pounded into me when I read your post, and so help me, clicked on the 'parent' post you replied to.
I know better, but did so anyway.
I'm going to scrub my brain out with bleach now.
Down With Slashdot BETA!!! I've been around the corner and seen the oliphant; you can only abuse me from your perspecti
You need to explore 'Help & Preferences' to avoid this.
with this..
Moreover, the detection routine soaked up 64 percent of McAllister's 1.6GHz Atom CPU
I can't stop laughing, I mean it took years for me to finally dump my beloved P3 1ghz, and I feel the pain of seeing your light weight processor struggle under the load... Of what, a possible future UI element? Either way, to include that snippet in the summary was beyond hilarious. Methinks he should just go spend 50 bucks at Newegg and get a dual core AMD processor if processor usage in this case really does warrant such attention.
On the Oregon Cost born and raised, On the beach is where I spent most of my days
...released Touchless SDK for a test spin, controlling his Asus Eee PC 901
Although McAllister was able to draw, scroll, and play a rudimentary game with his tomato, the SDK still has some kinks to work out. 'For starters, its marker-location algorithm is very much keyed to color,' he writes. 'That's probably an efficient way to identify contrasting shapes, but color response varies by camera and is heavily influenced by ambient light conditions.' Moreover, the detection routine soaked up 64 percent of McAllister's 1.6GHz Atom CPU, with the video from the Webcam soon developing a few seconds' lag that made controlling onscreen cursors challenging.
Perhaps a machine would be in order that didn't go to the extreme of energy-saving and low-quality manufacturing. Start from the top side and then work down.
Twitter supports and protects racists - by smearing their critics with the "Hate Speech" label.
It has been available commercially for a while. The dutch distributor of acorn (yes, that one) showcased it in, oh, '97 or so. That distributor had a clear business focus on retarded kids. Guess who's all grown up now?
Okay, I know it's a little late to post this, but these are the numbers I'm getting from my EEE 900. I'm running a 3-tap FIR filter to average all the pixels in a dummy frame. This doesn't include the time it would take to pull the frame from the CMOS/CCD sensor.
On battery alone:
On AC its a little better
Given the sensor resolution is 1280 x 1024, it appears their algorithm uses the full resolution. They could probably get much better results if they used 320 x 240. A little speed binning goes a long way.
Respond to this post if you're interested in the code.
The society for a thought-free internet welcomes you.
McCain may be old but he won't be having a heart attack as soon as he gets into office. If he was going to have one, hes under enough pressure just campaigning.
http://www.youtube.com/watch?v=a25jieLVOgw&feature=related
APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
...and one of the first things they did as a sample was to write Pong.
Finally! Game play has come full circle.
http://communityclips.officelabs.com/Video.aspx?videoId=a89a217b-fc38-4a6c-87f8-ab59a2028391