Jerry A. Dicolo, writer for Dow Jones Newswires, wrote a fascinating piece in the Wall Street Journal about the emergence of 3D camera technology in consumer electronics. As computer manufacturers race to incorporate the latest touch screen functionality, another group of companies are working toward the next wave of interface technology, gesture recognition in 3D space.
Using sophisticated depth sensing camera technology, companies like Softkinetic are able to design interface software that reads a 3 dimensional image of a room. The specially designed software can then interpret the movment of a person into input commands. This technology will allow us to adjust the volume of a television with the twirl of a finger, or zoom in on an image by leaning forward. Theoretically it could become accurate enough for your computer or television to recognize individual faces.
Many people believe this technology will be available to the mass market within the next year, being implanted in televisions and sold as an accessory to video games. Right now there are two main impedements for this technology; the high cost of 3D cameras and the extensive processing power needed to interpret the immense amount of data from 3D cameras.
“What’s new here is that you can do it on a consumer-based device and you can do it well,” said Michael Steele, head of Nvidia Corp.’s visual computing business. “It’s not really ‘Star Trek’ anymore. It’s all really happening right now.”