San Francisco based start-up 3Gear Systems has developed a gesture control system with an astonishing finger-precise hand gesture tracking. The system uses two Microsoft Kinect sensors facing downwards from above a desk and a new software to track a user’s hands.
When properly calibrated to the user, the system provides millimeter-level accuracy of the user’s hands. This allows to build simple and intuitive interactions that leverage small, comfortable gestures: pinching and small wrist movements instead of sweeping arm motions, for example. Gear has released an open software library for 64bit Windows to let developers integrate the technology into their applications. Two Kinects and an own self-made rig to mount them is required. Commercial licenses will be available later.
3Gear developed a new computer graphics algorithms for reconstructing the precise pose of the user’s hands from 3D cameras. A key component of the algorithm is to use a database of pre-computed 3D images corresponding to each possible hand configuration in the workspace. The 3D image database is efficiently sampled and indexed to enable extremely fast searches. At run-time, the images from the 3D cameras are used to “look up” the pose of the hand using the database. This way, the user’s hand pose can be determined within milliseconds — fast enough for interactive applications