Spatial-temporal features by image registration and warping for dynamic gesture recognition

In this paper, we present an approach to isolated gesture recognition, which uses as input the monocular sequence of dynamic gesturing with the single hand. We use the direct method of motion estimation, and realize gesture segmentation by image registration and warping based on robust A P-estimator and the dominant motion model. After extracting the spatial-temporal features of gestures, we perform dynamic time warping (DTW) to recognize 12 types of control gestures (6 for translation, 6 for rotation) replacing the 3-D mouse tool. A small demonstration system has been set to verify, our method, i.e. controlling a panorama image (set by mosaicing a sequence of standard “Garden” images) viewer with gesturing