Robotic Gesture Recognition by Cue Combination

Abstract. Automatic gesture recognition holds the promise of making man-machine interfaces more natural and intuitive. We discuss six requirements for gesture recognition by robots. We present computer vision techniques developed at our lab which are suited to meet the requirements. The techniques owe their robustness to the combination of several cues for a particular task instead of relying on a single cue alone. We demonstrate this in a sample application employing a real robot in a pick-and-place scenario.

• Type: Conference
• Year: 1998
• Where: GI
• Authors: Jochen Triesch, Christoph von der Malsburg
• Keywords: Automatic Gesture Recognition, Gesture Recognition, GI 1998, Man-machine Interfaces, Theoretical Computer Science