Softkinetic, a company based in Belgium, is working to let video-game players use a wider range of more-natural movements to control the on-screen action. Softkinetic's software is meant to work with depth-sensing cameras, which can be used to determine a player's body position and motions. In this whole body gaming, there is no need to wear a special outfit.Designing programs that work with the cameras, however, is difficult: translating depth measurements into a map of a human figure, and determining what motions that figure is making, are computationally daunting tasks. This is where Softkinetic comes in.
Softkinetic's technology started out as research at the University of Brussels, in Belgium, aimed at exploring the user interfaces made possible by stereoscopic cameras, which sense depth by using two input sources, in much the way that the human brain perceives depth by comparing data from two eyes. The group created Softkinetic in mid-2007 and has adapted its research to work with newer depth-sensing cameras as well.
The new cameras sense depth by using infrared light in one of two ways. First, the camera might send out infrared light and receive the reflections of that light off objects in a room. The sending and receiving information can be compared to determine details of position and depth around the camera. Alternatively, the camera could project a grid of infrared light onto a room, and calculate the positions of objects based on how the grid is distorted.
Whatever the specific depth-sensing tactics of a given camera, Softkinetic aims at developing a software which is built to work with the four major depth-sensing cameras on the market, including the ZCam from 3DV Systems, With Softkinetic's software, game designers can avoid retooling their applications to work with each of those cameras.
Interpreting data from different types of hardware isn't the toughest part that Softkinetic does. To classify the scene and how to find the player and remove the rest, and reconstruct the person's structure is the difficult part regarding the developing of software. The first half of that task involves filtering out a great deal of noise from the signal. For this it’s need to zoom in on the important thing i.e. the player, and not the person next to you sitting on the couch and making fun of you. Secondly, the software creates a 3-D volume from the fuzzy cloud of points the camera detects and identifies body parts important to an application. So instead of interacting directly with the depth map produced by the camera, designers get information from Softkinetic's software about which body parts are moving and how quickly. The company has also identified sets of gestures people commonly make when trying to control a program in a particular way.
It’s a really exciting thing for the field, and not just for gaming. For example: knowing a person's body position could help with applications such as health-care monitoring in the home, or other
applications in the field of ubiquitous computing.
