Real-time fingertip tracking and gesture recognition (original) (raw)
2002, IEEE Computer Graphics and Applications
A ugmented desk interfaces and other virtual reality systems depend on accurate, real-time hand and fingertip tracking for seamless integration between real objects and associated digital information. We introduce a method for discerning fingertip locations in image frames and measuring fingertips trajectories across image frames. We also propose a mechanism for combining direct manipulation and symbolic gestures based on multiple fingertip motions. Our method uses a filtering technique, in addition to detecting fingertips in each image frame, to predict fingertip locations in successive image frames and to examine the correspondences between the predicted locations and detected fingertips. This lets us obtain multiple fingertips' trajectories in real time and improves fingertip tracking. This method can track multiple fingertips reliably even on a complex background under changing lighting conditions without invasive devices or color markers. Distinguishing the thumb lets us differentiate manipulative (extended thumb) from symbolic (folded thumb) gestures. We base this on the observation that users generally use only a thumb and forefinger in fine manipulation. The method then uses the Hidden Markov Model (HMM), 1 which interprets hand and finger motions as symbolic events based on a probabilistic framework, to recognize symbolic gestures for application to interactive systems. Other researchers have used HMM to recognize body, hand, and finger motions. 2,3 Augmented desk interfaces Several augmented desk interface systems have been developed recently. 4,5 One of the earliest attempts in this domain, DigitalDesk, 6 uses a charge-coupled device
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.