June 28, 2004
Gesture Interfaces
Beyond keyboards, weather forecasting, and games, gesture recognition technology could transform the way people interact with computers in a variety of settings. Universities have been working on the technology for years. Researchers at the Georgia Institute of Technology, for example, have explored how gesture recognition may help reduce automobile accidents. A group led by Thad Starner has created what it calls a 'gesture panel' in place of a standard dashboard control. The driver adjusts the car's temperature or sound system volume by maneuvering her hand over a designated area, without having to take her eyes off the road.
Researchers at MIT's Media Laboratory have studied ways in which gestures could be used to enhance various entertainment devices. A 'StoryMat', for example, could recognize and react to movements of particular toys on a child's play mat. A 'conversational humanoid' senses and responds to a person's motions, as reported by a wearable, electromagnetic tracking device. Other projects examine the emotional messages that gestures and posture convey. Research has shown that it's possible to program machines to discern the interest or lack thereof that children display when interacting with educational software, says Rosalind W. Picard, director of the lab's affective-computing research group. A program that incorporated such inadvertent user input could respond accordingly—perhaps by switching activities when the user slumped in apparent boredom.
Tech Review article: Computing Gets Physical
Full article here.
Posted by sfisher at June 28, 2004 12:21 PMComments
Saw this presented at Starner's Keynote at the ACE conference a few weeks back. Georgia Tech's gesture stuff looks far and away the best that I've seen. In general, I more or less disagree with the notion that gesture recognition is better than traditional input... however, the stuff that gt is doing is a more subtle way of tracking gestures, and one that I think works better and has more far reaching applications. For example, there are a ton of papers showing how minority report can become a reality (cough, IMSC, cough). BUt the problem with this is that users have to learn a complex vocabulary in order for these gestures to be recognized, and then even after that, gestures often have to be repeated, etc, in order to get them to work. "The Clapper" would be completely useless if you had to clap in a specific sequence, or if your claps weren't loud enough, etc. Same with much gesture research. Seems like it needs to be a) seemless and b) highly accurate before we can start judging how useful it can be. So bravo to all these researchers trying and in many cases failing to meet both the above criteria. I have no doubt they'll get it sooner or later and then we can start approaching it from a usability perspective.
Posted by: William Carter at June 28, 2004 12:44 PM
Yes, once this is all ironed out it will be vey exciting to find applications for it. At E3 I saw a presentation by some of the EyeToy team. They had some video clips of the research that is going into the next generation of EyeToy. Three things the spoke of excited me most 1) the ability to attach a IK bone structure to the VUP 2) Depth cues can be sensed allowing for potenial Spatial interface that extend beyond the current 2D manifestations 3) Simple mask effects so system elements can move behind the VUP.
This could all lead to some great creative potentials!
Posted by: SEDinehart at June 28, 2004 06:17 PM
What are some of the gesture runtimes available?
Posted by: mmlifter ![[TypeKey Profile Page]](http://interactive.usc.edu/nav-commenters.gif)
at March 16, 2005 03:24 AM
Post a comment
Thanks for signing in, . Now you can comment. (sign out)
(If you haven't left a comment here before, you may need to be approved by the site owner before your comment will appear. Until then, it won't appear on the entry. Thanks for waiting.)
