1A1-C13 濃淡値の時系列変化を利用した周期ジェスチャの認識

概要

論文の詳細を見る
In this paper, we propose a method to recognize periodic gestures from images as a key technology for human machine interface. The proposed method uses power spectrum and phase spectrum that are obtained by applying FFT to time series of intensity images. FFT is applied to each pixel of the low-resolution images. The method consists of 2 steps. First, the method detects periodic motion regions from power spectrum. Second, the system uses the phase spectrum in the detected periodic motion region to classify the gestures. The proposed method is robust to lighting condition and individual difference of skin color, because it does not use color information. To demonstrate the effectiveness of the proposed method, we have conducted several experiments and show that support vector machines are well suited for obtaining discriminate hyperplanes for recognition of periodic motion.
一般社団法人日本機械学会の論文
2009-05-25