Archive for the 'Elsewhere' Category
Tom Warren over at winrumors.com has suggested that the official Microsof Kinect SDK may be released in beta form later today. I currently have my fingers crossed that this is the case.
The software giant will unveil its plans for the forthcoming Kinect for Windows SDK beta at MIX11 this week. According to sources familiar with the company’s plans, Microsoft will announce the beta availability on Wednesday April 13. WinRumors previously exclusively revealed that the software giant was planning its own SDK amid a growing community of “Kinect hackers”. Microsoft officials confirmed the existence of the Windows based Kinect SDK during a special press event in February. Microsoft’s Don Mattrick, president of the company’s interactive business division said the software maker will ship the SDK in the Spring. The beta is on schedule and will likely be made available on Wednesday.
As a side note Sony is also planning to allow developers to use its PlayStation Move technology as an input device, with the launch of an official SDK.
Move.me is an software server application, designed for academics, college students, HCI developers or anyone with a programming interest. Sony says it wants to see how people can take the PS Move beyond gaming, and looks forward to seeing tools developed in areas such as fitness, rehabilitation, learning and the creative industry.
Developers will be able to use the PS Move controller, the PS3 system, the PlayStation Eye camera, and a PC, in their quest to build innovative applications. As with Kinect tho release date for the SDK has been detailed only as this spring. More information can be found via Sony’s Move.me webpage.
Here is a video that I should have put up a long time ago featuring an interview between Larry Larsen
and Microsoft Principle Researcher Bill Buxton.
For more information check out Channel9‘s origional posting.
Here we have a video of Microsoft is showing off how it is using normal cameras to create 3D scans of people or objects. The company has posted videos of how the technology works.
Microsoft uses 2D images from webcams or the Kinect sensor to create a 3D model of a face that can then track head movements and portray them on a virtual 3D avatar.
Stevie Bathiche demonstrates the “wedge lenses” that can pick up activity above a surface using cameras (including Kinect) mounted below a flat screen.
The wedges are used to transmit light back out the other way as two separate images to create an auto-stereoscopic image to allow for glasses-free 3D in displays.
This morning Microsoft announced plans to release a non-commercial Kinect SDK for the Windows platform. This is great news for Windows developers like myself as currently development for the platform is lagging several steps behind that of the other operating systems, resulting from the legacies of cross-platform development.
In context OpenGL is great but its not DirectX!
The Kinect for Windows SDK is being developed and released by Microsoft Research in collaboration with IEB. It will be available (hopefully) this spring as a free download, and will give academic researchers and enthusiasts access to key pieces of the Kinect system, such as the audio technology, system application programming interfaces and direct control of the Kinect sensor itself.
BrainDriver is an AutoNOMOS project with the purpose of controlling a car by thoughts using the Emotiv EPOC headset.
The BrainDriver is not roadworthy yet but suggests that in the future human-machine interfaces like this could have huge potential in combination with autonomous driving.
For more information check out http://autonomos-labs.com/
People detection using a Kinect. The camera can count any number of people and roughly estimate their height. Note that there is no tracking here, just independent detection in every frame.
This sequence is processed in replay mode, the actual framerate is higher (~5Hz) when images are being grabbed online. See http://nicolas.burrus.name/index.php/Research/KinectRgbDemoV4 for more details and opensource software.
The following video by Oliver Kreylos demonstrates a first test of merging the 3D video streams from two Kinect cameras into a single 3D reconstruction. The cameras were placed at an angle of about 90 degrees, aimed at the same spot in 3D space.
The two cameras were calibrated internally using the method described in the previous video, and were calibrated externally (with respect to each other) using a flat checkerboard calibration pattern and manual measurements.
New software version with support for multiple Kinects is available for download via Oliver’s website: http://idav.ucdavis.edu/~okreylos/Res…
Wonderfull stuff 
The following video demonstrates python script for Blender using Brandyn White’s work on the libfreenect setup.
It shoots out a point cloud of what the Kinect sees into Blender, where you can export to PLY or any of the other formats Blender supports. This will also allow you to put this into something like Meshlab (or use Blender scripts that do the same thing) and get a 3D model of whatever the Kinect is seeing.
For more information and for the source check out the following link: https://github.com/geckoslayer/blenderkinect/blob/master/