Slashdot Mirror
Kinect Hacked, Adafruit Bounty Won
scharkalvin writes "Adafruit has announced a winner to their bounty for an open source driver for the MS Kinect. From the article: 'We have verified that it works and have a screenshot from another member in the hacking community (thanks qdot!) who was also able to use the code. Congrats to Hector! He's running all this on a Linux laptop (his code works with OpenGL) and doesn't even have an Xbox!'" We talked about Adafruit's bounty yesterday.
that certainly didn't take long. Congratz.
Two of my imaginary friends reproduced once
Making stuff work is a crime.
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
Finally, a motion sensor for a computer... /*sarcasm*/
"Using a linux laptop". . Now every geek that has avoided Microsoft and their products like the plaugue will be rushing out and buying Kinect controllers. .
Step One: Create a toy that will entise the Open Source crowd
Step Two: Wait for some one to get it to work on their linux box
Step Three: watch all the geeks and hobyists buy said toy
Step Four: Profit
Hacking is good for business.
. .
I've always wondered about that statement - did Microsoft really mean people hacking Kinect the hardware, or did they refer to the new round of cracking going on in the Xbox360 community after Microsoft rolled out the Fall Update?
After all, iFixit's tear down doesn't reveal any anti-tamper mechanisms - no potting of circuit boards or anything. Unless they meant firmware hacking to try a USB jailbreak for the 360, but that's simple to do without needing a $150 piece of equipment.
The Fall update did bring out anti-modded-Xbox protection measures. Backup games fail a new check and the results get reported back to Microsoft, who can institute a new round of console bans (but only if you're stupid enough to connect to Live with your modded Xbox360). I'm just wondering if some new PR person got the explanation all jumbled up or something between the engineers, legal and PR made a very interesting game of telephone.
I can see how going from "The software update we rolled out for Kinect contains new anti-piracy measures" into "Microsoft takes strong measures against those who tamper with Kinect". Or how a simple query by someone asking for drivers to Microsoft gets turned into a request for the Xbox360 software itself leading to silly statements. Add in 20 layers of management that the message gets filtered through and it's what you end up with.
Wow he got a webcam to work on his laptop! Amazing!
Sense depth and produce a heat map, for starters.
If I mod you up, it doesn't necessarily mean I agree with what you've said, sorry.
Depth perception.
I wonder how well it would perform under horticultural LED lighting with no green emissions.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
What'll you bet that Microsoft rushes out a new, less hackable version. There aren't so many of these in the field that it wouldn't be worth their while. Or are they just planning on using patent takedowns to make it illegal to work with the data stream produced by a Kinect box?
Which brings up an interesting (to me, at least) topic. Once you buy a product that legally implements a patent, aren't you implicitly granted a license to use that patent? To me, if you have, for example, a license to have an exchange-based email account, you've got implicit license on all patents governing access to that account (or at least access to features covered by the account license). Otherwise, what value does the account license have? Likewise, having bought a PC with a (paid for) Windows license covering codec patents, etc, why do I not have an implicit patent license to access those codecs (at least on the machine for which I bought the license). Come to think of it, in the case of the 'decode' side of a codec, why doesn't the encoder's patent license enable me to decode the stream with the software of my choosing? In each case, somebody's paid to use these patents. It sure feels like in all these 'creator vs viewer' situations, we're getting double-charged on patent rights, no?
Posted from my Android phone. Oh, I can change this? There, that's better...
Wow, you didn't even watch the video. Well, it apparently knows depth/distance among other sensory data. Robotics applications should be obvious (as also stated in the video) but I'm sure there are pornographic uses as well.
Measure depth. And capture 4-channel audio with spatial location and echo cancellation (unconfirmed but likely). It also moves up and down and has an accelerometer. People are mostly interested in the depth thing, though.
The question should be:
"Now what exactly can this do that any shitty 18-axis joystick can't?"
That's the kind of data you receive on the cable. Just like with optical mice, you don't have access to raw imaging device output, only processed through the image recognition layer.
45 5F E1 04 22 CA 29 C4 93 3F 95 05 2B 79 2A B2
All I saw was a webcam and IR video output. People were thinking 2 grand was too low a bounty... now I'm thinking, he got 2K for that?? Doesn't seem very useful unless this hack can also get to the processed gesture data. Or is all the processing done on the XBox?
marcan, Will we have a wii port ? :)
This guy is on the way to solving the three main problems of personal robotics:
1. Indoor localization (figure out where you are inside)
2. Indoor navigation
3. Table top manipulation
There are already open source software packages for all of these items, but they require very expensive laser scanners (starting at 5K a pop). Most of these lasers only scan one row at a time, which means that for situations where you want 3D, you have to tilt the scanner up and down. This is a hassle and leads to slow scan times, which reduces the responsiveness of the robot.
For indoor localization, what you really want is just a line of points at a fixed height (you could extract one row of Kinect depth pixels) that you can feed to particle filers to figure out position in a mapped space. You might also be able to use opensource SLAM software, wheel encoders, and a Kinect to make 2D and 3D maps of indoor environments.
For indoor navigation, you can use 2D navigation planners to figure out plans through maps, and then use indoor localization to follow the plans. The Kinect can serve as an obstacle detector in addition to the providing data to the localizer. For example, if a person or animal jumps in front of the robot, the Kinect will sense it, and allow the robot to stop instantly and plan a new route. With a tilting laser, the reaction time would be slower, because laser might be in an orientation where it does not see the obstacle.
For table top manipulation, the Kinect can provide a point cloud of the objects on the table. CV software can remove the background (table, wall, etc.) and then detect the objects on the table. Once this is done, motion planners can plan a route for an arm or other manipulator to pick up objects on the table.
Once we have all three of these systems, it should not be all that hard to link them together and start actually doing useful things with robots in our homes. Even just the first two would make it possible useful cleaning and sentry robots.
Responsibility is an addiction
Virtue is a temptation
Community is a cartel
Congrats with the hack & bounty marcan! It seems that nothing is unhackable in your hands, well done!
This sig is intentionally left blank
Just think.. your fav porn site can now see just how hard your spanking your monkey, and suggest videos based upon how much you enjoyed previous ones from that genre.
You are entitled to your own opinions, not your own facts.
are you suggesting you are a *cough* tomato plant *cough*?
Once we have all three of these systems, it should not be all that hard to link them together and start actually doing useful things with robots in our homes. Even just the first two would make it possible useful cleaning and sentry robots.
We theoretically approach useful home robotics, and your first thought is cleaning? Followed by sentry duties? What about the ole in-out-in-out, man? Where in the hell are your priorities?
"Cleaning." I swear some people are just too happy to announce to the world "Hey, look at me! I have zero sense of imagination! Look how practical I am!"
Hey genius!
https://github.com/JoshBlake/OpenKinect
lolololololol almost spit coke on my laptop haha
Can they do that now? Remember so far the only (speculative) demand is for the cheaper Kinect. Has open source drivers and out of band usage for the Wiimote increased measurable sales?
OK now bring on the PS3, Wii,Linux and indie games before MS brings on their own.
<evil grin>
No, I'm suggesting it for the large horticultural production systems I design for large food production companies.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
My kingdom for modpoints.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
Id keep up my whining but do nothing, while I take notes on "innovative" ways to exploit the technology as people develop on it for free.
Then take their idea and if they complain, threaten them for breaking the EULA, or something along those lines.
"Enjoy what you're doing! If it becomes drudgery, you're doing it wrong!" - Jim Butterfield
http://games.slashdot.org/story/09/06/12/0450237/Why-Natal-Is-a-Big-Deal
If I were MS, Sony, or Nintendo, I'd be paying close attention to people in the community that start doing interesting things with this and put them on my short-list for recruiting people to develop next-generation hardware.
OpenKinect
You cannot view the group’s content or participate in the group
because you are not currently a member. Members must be approved
before joining.
You must be a member of this group to read its archive.
Apply for membership or contact the owner.
Yep..Standard practice for sensibly run email groups.
It is difficult to get a man to understand something when his job depends on not understanding it.
This is the camera and IR depth sensor but has anyone figured out how to talk to the microphones, electric motor and other stuff in there yet?
Hey, can we get the captcha they have on adafruit here on /.? That thing is awesome.
He's gonna feel pretty silly, rejecting the $3k and asking for donations to make it $10k.
They could always bring back Clippy:
"It looks like you're trying to abuse yourself. Would you like assistance with pornographic material? Yes No"
This is a somewhat different thing from what Johnny Lee did, though. Johnny took existing Wiimote driver code and used it to do some very cool things with the data, such as his famous head tracking demonstration. He didn't figure out the actual communications protocol, though (in fact, I did a lot of the early Wiimote reverse engineering hacks too; I guess I have a thing for wacky game controllers!).
Unfortunately for us engineers and low-level hackers, the people actually finding practical algorithms and cool uses for these devices tend to get more attention than the people hacking the low-level details ;). I'm genuinely excited to see what computer vision experts can do with the raw Kinect data, though (I personally can't do much more than apply a cheap heat map to the data like I did in my video).
If I were MS, Sony, or Nintendo, I'd be paying close attention to people in the community that start doing interesting things with this and put them on my short-list for recruiting people to develop next-generation hardware.
They already do. Just keep in mind that there are relatively few talented grad students doing useful stuff which the public never hears about (some of whom Microsoft finds and hires), and orders of magnitude more amateurs duct taping crap and putting videos on Youtube.
Amateurs from the community are usually late to the game, and their implementations lack technical depth.
then the follow-up question is.. why do those need depth perception in the form of stereoscopic vision instead of e.g. ultrasonic or laser range finding?
Depth perception helps a bit when you have to look down long rows of channels.
I would have much rather had this camera with dual RGB sensors instead of one RGB and a depth/heat sensor for this purpose, however.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
Lets start with This Guy, which happens to work for Microsoft now.
Now considering that Kinect can track depth and location relative to Kinect placement, which is usually under the TV, it should be trivial to do the above head tracking minus the special headgear. In Fact, I would be surprised if a game doesn't do this with Kinect sometime in the future to simulate glasses free 3D that works on any TV. Now I know that Webcams now can do this (the droid does site is a real world example) but since they cant measure depth like Kinect, the effect isn't as eye popping like it is in the Johnny Lee video.
Now imagine this on your PC. I can't imagine Microsoft missing an opportunity to make more money selling a Kinect for PC's sometime in the future, but then again, it's been over three years and I still can't use the Xbox 360 chatpad on my PC.
In Soviet Russia, Trojan exploits YOU!
Nice, lets all remember that you were the first person to think of using a robot that watches how hard you spank it to determine what kind of dirty stuff you're into the most. Like a functional MRI for porn. You should slap a patent on that one.
It would be a little creepy though... Just don't make the robot too human-like or it could really distract.
Synergy is your friend
Then just buy two webcams instead.
Chairs will be flying.
It is already amazing what can be done with an optical camera.
However using depth images Andrew Johnson did some impressive work on recognising objects in 3D depth maps. And Dan Munoz recently worked on applying this kind of algorithms to Willowgarage's PR2 robot. With your Kinect driver, depth sensors are getting within reach of hobby developers.
Of course, it's also possible Microsoft deliberately spun this "feature" as hype to generate "buzz". They set a trap in the form of a challenge,
and we fell right into it. They've now been handed working drivers for other platforms on a silver platter, along with a vast number of potential customers they didn't have before, and a slew of free "viral" advertising resulting from our "victory".
What other reason could they possibly have for (ostensibly) restricting sales of this hardware?
That's one theory. The only other I can postulate is that Microsoft are a bunch of idiots.
Either Microsoft has been very clever, or very stupid. Take your pick.
If he just buys two webcams he still has to write software to put them together. The big deal about Kinect is that it's a blob of hardware which already does this stuff for you.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
How so ? How can a contract grant exceptions from a law ?
That's because the copyright law is designed that way.
Basically, the copyright law says :
- Thou shall not copy. Unless you are the author or get a permission.
Then the GPL says :
- I'll give you this said permission to make copies and give them to others. But in exchange, keep this permission, so the next users too can benefit from the same freedom.
Or the BSD says :
- Here's the permission to make copies and give them to others. If want to change the game and not give this permissions to the next in chain : fine, do it.
Contrast to the EULA :
- You wanted a permission to copy ? hehe. Too bad. You won't get one. Not only you won't get a permission to copy (so technically, it's *NOT* a copyright license). But in addition we'll throw in a bunch of crazy requirement and request for sacrifice of first-born, just so you can use what you've legally bought.
A license can grant an exception to some law, if said law says that you have an exception if you receive an authorisation, and said license is the corresponding authorisation.
GPL and BSD give the right to copy even if copyright normally forbids copying, because copyright say that you need a permission and GPL and BSD *are* the permission.
(Well it's an over simplification :
- not copy: there are fair use exception. depending on your jurisdiction, these exception might including citation, academic, backup, format-shifting, caching, loading into RAM. Even blowing up DRM if it stands in the way (alas, not in all jurisdictions)
- author: holder of the intellectual property, to be more precise. you could have bought the rights over it from the actual author and now it's your.
- permission: that is what the word "license" initially meant, before EULA started to turn it into the restriction-fest we know.)
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
I will be the first to say *please please please!!!"
Ubuntu is an African word meaning 'I can't configure Debian'
Check youtube for the IR google videos of how kinect works. It's not just two webcams, it's also an IR projector to do depth mapping much more successfully than just "two webcams". It's really quite a clever tech, and means that localized contrast issues (dark room, etc) won't matter for depth mapping (but will matter for image recognition).
Fellow Slashdotters, your opinion on this please: now that the Kinect is actually useful, for how long do you think they will be available before Microsoft changes something so that the open-source drivers don't work?
I want to know whether to go buy one now before Microsoft retires the current model and starts putting other models out with new firmware that won't work with the drivers.
Currently I don't have any use for one, but I do have a bit of disposable income, and wonder whether it would be useful to sink US$150 (if that's what it costs as mentioned in another post) into one so that when software comes out for it, I won't be stuck reading "This does not work the newer models of Kinect" or something.
Your opinions would be appreciated. Thanks.
404555974007725459910684486621289147856453481154 in hex is "You sank my Battleship?"
[GPG key in journal]
That's exactly what I was thinking.
Especially since MS is being protective of the Kinect SDK
true that.. but why are you looking down long channels exactly? Are you trying to reduce cost involved with an overhead rail system by just using a single rail along the rows?
thanks for taking the time to respond, btw :)
The kinect Z-sensor works by sending IR flashes and measuring the response time at the pixel level. They work well in the 1.8 to 2.7m. That probably makes it worthless in your case. If you need a bigger range, there are rangefinders that can be useful but that are bigger and more expensive. The best one is this one ( http://www.hizook.com/blog/2009/01/04/velodyne-hdl-64e-laser-rangefinder-lidar-pseudo-disassembled ) it does 1m-80m with down to 1cm of precision. But it is in another price range (last year it was $15,000)
The Wise adapts himself to the world. The Fool adapts the world to himself. Therefore, all progress depends on the Fool.
Actually it is a z-cam, it doesn't use stereo. The sensor really meaures a distance like a range finder on each pixel of the sensore. Really nice tech that used to be very expensive. That's why so many people are excited about it.
The Wise adapts himself to the world. The Fool adapts the world to himself. Therefore, all progress depends on the Fool.
Would love to see someone hack the firmware and get it to work on a playstation or wii. That would be a wonderful hack. =)
Replying to myself may be a sign of mental breakdown, but I did want to point out the following web page, listed under Google as having only appeared an hour ago (2300h UTC) stating everything that the main article says, with the addition of:
"Microsoft is not amused by the open source software community's effort to build its own Kinect drivers. The company says that it doesn't condone reverse engineering and has vowed to use technical and legal measures to prevent unauthorized third parties from repurposing the Kinect camera."
There is no attribution and I don't know where they got the statement. I guess as time goes on we'll find out.
http://arstechnica.com/open-source/news/2010/11/microsoft-not-amused-by-open-source-kinect-drivers.ars
So, I guess I should go buy one.
404555974007725459910684486621289147856453481154 in hex is "You sank my Battleship?"
[GPG key in journal]
Auto-adjustment of lighting to prevent the plants from growing up into the light itself and blocking out the other plants from getting light.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
Yeah but two cameras with two totally different views of the subjects would give you even more data than it has, so there is merit to the approach and indeed it is used. It takes more processing power but that's cheap nowadays. The advantage of this is more in robotics or just in your living room where expecting people to set up two cameras and leave them set up and unoccluded is unrealistic at best. And of course to the hobbyist the most massive advantage is having it done for you :)
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Dear Author, Nice written,Look forward your updates,I also like this,thank you,Cheap Nike Shoes , Nike Shox On Sale at shoes-vip.com,Discount and Free Shipping,Save43%-60%