Kinect Digest

 

Kinect Project Merges Real and Virtual Worlds

Technology Review (09/30/11) Nic Fleming

Microsoft researchers recently demonstrated KinectFusion, a research project that lets users generate three-dimensional (3D) models in real time using a standard Kinect system. The technology enables objects, people, and entire rooms to be scanned in 3D. "KinectFusion is a platform that allows us to rethink the ways that computers see the world," says Microsoft researcher Shahram Izadi. The Kinect projects a laser dot pattern into a scene and searches for distortions using an infrared camera, which generates a point cloud of distances to the camera that the Kinect uses to identify objects and gestures. As a KinectFusion user waves a Kinect around a scene, an algorithm called iterative closest point (ICP) combines data from snapshots that are taken at 30 frames per second to create a 3D representation. ICP also can track the position and orientation of the camera by comparing new frame data with previous frames. "With KinectFusion, anyone can create 3D content just by picking up a Kinect and scanning something in," says Microsoft researcher Steve Hodges.

View Full Article http://www.technologyreview.com/computing/38731/

 

Microsoft's Kinect: The New Mouse?

New York Times (02/22/11) Steve Lohr

Microsoft researchers say the company's Kinect technology, which recognizes gestures and voice commands, could be the beginning of a new way of communicating with computers. Microsoft's Craig Mundie says that Kinect is a natural user interface that could lead to computers that understand human speech and hand gestures in the future. Kinect is the "first incarnation of the next big thing in computing," Mundie says. Microsoft recently announced plans to release a software developer's toolkit for academics and enthusiasts that want to design their own applications using Kinect technology. Microsoft's Don Mattrick says the company is "embracing that community. This is the next step in that journey." Meanwhile, Microsoft's researchers are developing applications that take advantage of the Kinect's ability to recognize a wide variety of physical objects. They say Kinect technology could be used for inexpensive three-dimensional design and modeling, realistic human avatars, and smart displays.

“There’s not a button or a switch,” said Peter Lee, managing director of Microsoft’s research lab in Redmond. “It’s just you. The success of Kinect shows a pathway to go forward.”

View Full Article http://bits.blogs.nytimes.com/2011/02/22/microsofts-kinect-the-new-mouse/

 

Controlling a Quadrotor Using Kinect

My colleagues working on the Flying Machine Arena (or FMA) at the ETH Zurich have just posted a video of their latest feat: A natural human-machine interface for controlling their quadrocopters.

http://www.idsc.ethz.ch/Research_DAndrea/FMA

http://spectrum.ieee.org/tag/quadrotors

Until now, visitors of the FMA could use a magic wand like the one in the right picture to send quadrotors racing through the 10x10x10m space. As shown in the video, the addition of a Kinect now allows a far more natural and intuitive interaction.

http://www.youtube.com/user/ETHZurichIDSC#p/c/CFEA331BA502D696/0/xx3rsadZA6M

What's next? I vote for using the new interface to have Asimo directing the FMA's dancing quadrocopters to the Quadrocopter Opera!

http://spectrum.ieee.org/automaton/robotics/robotics-software/quadrotor-interaction

 

Top 10 Robotic Kinect Hacks

Microsoft’s Kinect 3-D motion sensor is starting a small revolution not only in video games but also in robotics. Kinect has already sold more than 8 million units, and roboticists all over the world are finding amazing applications for the sensor. Check out our 10 favorite hacks, which include using Kinect to control a flying quadrotor, operate a surgical robot, and make a humanoid cut a banana with a knife.

http://spectrum.ieee.org/automaton/robotics/diy/top-10-robotic-kinect-hacks

 

MU Researchers Use New Video Gaming Technology to Detect Illness, Prevent Falls in Older Adults

MU News Bureau (MO) (09/06/11) Samantha Craven

University of Missouri researchers are using motion-sensor technology to monitor changes in assisted-care facility residents. For example, Missouri professor Marjorie Skubic and doctoral student Erik Stone are using Microsoft's Kinect device to monitor behavior and routine changes in patients, which can indicate increased risk for falls or early symptoms of illness. "The Kinect uses infrared light to create a depth image that produces data in the form of a silhouette, instead of a video or photograph," Stone says. He says using Kinect can alleviate "many seniors' concerns about privacy when traditional Web camera-based monitoring systems are used." Meanwhile, Missouri professor Mihail Popescu and doctoral student Liang Liu developed a fall-detection system involving Doppler radar, in which the system identifies changes in walking, bending, and other movements that could reveal an increased risk of falling. "If emergency personnel are informed about a fall right away, it can significantly improve the outcome for the injured patient," Liu says. Both motion-sensing systems provide automated data to care providers, alerting them when a patient needs help.

View Full Article http://munews.missouri.edu/news-releases/2011/0906-mu-researchers-use-new-video-gaming-technology-to-detect-illness-prevent-falls-in-older-adults/

 

The Motion Tech Behind Kinect

In Microsoft's new Kinect gaming platform, a webcam-style add-on for its Xbox 360 console, the player has been turned into the controller. Kinect wouldn't have been possible without the help of an IEEE Fellow who worked on the system's groundbreaking real-time motion tracking. Read on at

http://theinstitute.ieee.org/technology-focus/technology-topic/the-motion-tech-behind-kinect779

 

 

Hackers Take the Kinect to New Levels

Technology Review (12/02/10) Timothy Carmody

Massachusetts Institute of Technology (MIT) Media Lab researchers have developed DepthJS, a Chrome Web browser extension that enables users to surf the Web using the Kinect gaming device. DepthJS uses JavaScript to translate hand gestures into commands that the browser can complete. The researchers plan to use DepthJS as the interface between different Web applications and Kinect gestures. "Getting Kinect's events into the Web browser is all about lowering the cost of entry to exploring and creating applications using depth information," says MIT's Dough Fritz. "Right now we are in that state of rapid change where people are remixing familiar interaction techniques with what feels natural." Adafruit Industries recently held a competition to find software that could connect the Kinect to a normal computer. Developers have submitted videos of different Kinect applications. "These videos are really just proof-of-concepts that show some of the possibilities for further development," says Adafruit's Limor Fried. Another major hurdle is translating gestures from humans for use by computers. Most Kinect games overcome this issue by matching users with an onscreen avatar that mimics the movements. Another solution could be using light projectors to create virtual objects that users can interact with.

View Full Article http://www.technologyreview.com/computing/26822/