Fourier principles for emotion-based human figure animation

Abstract

This paper describes the method for modeling human figure locomotions with emotions. Fourier expansions of experimental data of actual human behaviors serve as a basis from which the method can interpolate or extrapolate the human locomotions. This means, for instance, that transition from a walk to a run is smoothly and realistically performed by the method. Moreover an individual's character or mood, appearing during the human behaviors, is also extracted by the method. For example, the method gets 'briskness' from the experimental data for a 'normal' walk and a 'brisk' walk. Then the 'brisk' run is generated by the method, using another Fourier expansion of the measured data of running. The superposition of these human behaviors is shown as an efficient technique for generating rich variations of human locomotions. In addition, step-length, speed, and hip position during the locomotions are also modeled, and then interactively controlled to get a desired animation.