Realtime pointing gesture recognition and applications in multi-user interaction
ACIIDS'13 Proceedings of the 5th Asian conference on Intelligent Information and Database Systems - Volume Part I
Hi-index | 0.00 |
Information kiosks, building directories, and area maps are useful for visitors to explore a new large place. Although several digital information or map systems have been equipped with touch screens, many existing systems are still regular non-interactive screens to display static or dynamic information. This motivates the authors to propose an efficient and economic solution to transform existing non-interactive information kiosks and maps into natural interactive systems that can accept pointing gestures, a common type of gestures in communication between people. The authors' vision-based method exploits the visual geometrical characteristics of pointing gestures thus is independent from skin color and can recognize pointing gestures with various pointing objects, such as fingers, bare hands, hands with gloves, or any arbitrary pointing objects. Experiments show that a single regular processor can process up to 10 interactive maps with less than 17ms with the average accuracy of more than 90%. Furthermore, by using template matching, a user can get the detailed guidance for the best route into his/her mobile device just by capturing the information being displayed in the interactive map.