Microsoft is working to improve the accuracy of Xbox 360 motion-sensing add-on Kinect so that it could detect finger movement and hand rotation, Eurogamer understands.

Microsoft's Kinect team is said to be working "very hard" on a switching or compression technology that will allow a greater amount of data to pass through Kinect to the Xbox 360 console.

Kinect features are dictated by firmware so that they can be added and upgraded over time.

The depth sensor used by Kinect is also dictated by firmware – it is currently set at a 30 frames per second limit and a 320x240 resolution limit.

At a 640x480 resolution, however, Kinect could begin to detect fingers and hand rotation – an effective quadrupling of its accuracy.

The issue relates to the USB controller interface, Eurogamer was told. It is capable of around 35MB/s, but it only uses around 15/16MB/s.

This artificial limit is in place because multiple USB devices can be used at once on an Xbox 360. But Microsoft is working on a technology to allow greater throughput in this regard, Eurogamer understands.

If Microsoft achieves its goal it could double the spec of Kinect's depth camera with a simple dashboard update.

Microsoft had not responded to Eurogamer's request for comment before publication, but Digital Foundry's Rich Leadbetter described the potential accuracy improvement as "eminently doable".

Microsoft would need to "disable or lower throughput of game installs running from USB flash drives to free up additional bandwidth," Leadbetter said.

"All eminently doable though bearing in mind that Kinect 'only' needs 20MB/s for full res from both cameras.

"The resolution coming out of the depth camera via PC is indeed 640x480, but it is uncertain just how accurate the camera's sensor is.

"Additionally, processing four times as many depth pixels could slow things down more."

Last month Anton Mikhailov, a software engineer at Sony Computer Entertainment America's research and development department, told Eurogamer Sony turned down Kinect's 3D camera because of the limitations of the tech.

"In reality, the 3D cameras we surveyed and what Kinect ended up using, they're 320x240 resolution, so when you're talking about tracking fingers, or even tracking things like the rotations of your hand, you're working with 10x10 pixels," Mikhailov said.

"It's very hard to get anything useful out of it."

Mikhailov doubted Kinect's capacity to create a decent Star Wars game "because there are so many ambiguities, and it's nearly impossible to track the angles of your wrists".

If Microsoft's achieves its goal of improving Kinect's accuracy, however, Mikhailov could be proved wrong.

http://www.eurogamer.net/articles/2010-12-17-source-ms-quadrupling-kinect-accuracy

thats interesting i will get kinect when its 99 or at christmass 2011

so kinect is actually capable of 640x480 but is being downscaled due to a software limitation of transferring the data via usb and conerns of data processing speeds?

did i get that right?  very interesting, and here i thought the downscaling was to cut the cost of production.  i'm suddenly feeling a bit better about kinect's future.

So they could,but they aren't.Misleading title.

That's all well and good but it's all 'potential' and 'some-day' type of talk.  Just like 'Teh Cell'.   It looks great on paper, but doing something like this (Quadrupling the power of Kinect)  will more than likely take a lot longer than they hope.   I really believe that Kinect 2  (In the next gen, assuming it exists)  will have legitimate potential, but I don't think all the technology is here yet and won't be.    

And I also believe that you still need physical items so the hybrid will mix in some combination of the Move/Kinect. 

I still think 'Kinect' is a generation off.

Sounds good but little bit assumptive title.  They're looking into it - which makes sense - but no confirmation they will do it or when.

I do expect them to improve performance though, it would be unheard of not to now the basic firmware and libraries are in place.  Question will be how far they can push it without upsetting other aspects of 360 operation?  Time will tell.

Should be possible. Didn't the MIT Kinect hack already prove it ?

No, they could and they are working on it....so not really a misleading title.

OT: This would be damn good news for KINECT.

It's interesting and promising, but the title is misleading - 4x pixels i.e. 2x resolution per axis does not translate into 4x accuracy.

I'm sceptic about this. As far as I understood the article, it's pretty much just speculation by Eurogamer.

There are more problems than just USB bandwidth. First of all, using 640x480 instead of 320x240 from the depth sensor would mean the Kinect algorithms would have to process four times the data. If they weren't magically able to massively reduce the processing time Kinect needs, such a step would make Kinect's performance even worse because it would increase the lag even more.

The other problem is that the real resolution of the depth sensor would only increase by a small amount. On a normal webcam/digital camera, using 640x480 instead of 320x240 does of course result in four times the resolution. In the case of the distance sensor inside Kinect however, the real resolution is neither 640x480 nor 320x240, it's the number of infrared points the device projects into the room. (as seen in this video for example: http://www.giantbomb.com/forums/general-discussion/30/what-kinect-looks-like-through-ir-goggles-points-of-laser-light/464521/). And that number doesn't even increase by switching from 320x240 to 640x480. So using 640x480 would increase the accuracy a tiny bit, but the disadvantage of additional processing time might easily outweigh the small accuracy advantage. Most people would probably prefer the current accuracy with less lag than slightly better accuracy with even more lag.