| 1 (2007) | |||||||||||||||||
Abstract | |||||||||||||||||
| Abstract: In this paper we present a new method for extracting spatialtemporal features of dynamic gestures. We fully utilize the information of temporal motion and spatial luminance. In the first two consecutive frame the dominant motion model is used to calculate the gesturing motion, then it is combined with the result of static segmentation to segment the gesturing hand or arm from the background. The detected object region will be projected onto the successive frame with the predicted motion by Kalman filter. Experimental results of gesturing actions are given to show the efficiency of our method. | |||||||||||||||||
Publication details | |||||||||||||||||
| |||||||||||||||||