Sensor Data Processing Method Based on Observed Person´s Similarity for Motion Estimation

Some systems use machine learning techniques such as support vector machines to estimate human motions using acceleration sensors. These systems must acquire acceleration data to build a model. Therefore, it is difficult to estimate a newly observed person´s motions promptly. Moreover, a newly observed person must carry out sufficiently diverse and numerous motions to build a model. These are heavy burdens that must be borne to observe people. As described in this paper, we propose a method for sensor data processing using similarity in feature of motions between observed persons. This method is designed to achieve a balance between providing motion estimation for a newly observed person promptly and for maintaining precision of motion estimation. In this method, the system can estimate a newly observed person´s motions initially because the system uses a similar observed persons´ standard. We implement a prototype system to evaluate this method. The system estimates human motions using the acceleration sensor. We perform some initial experiments using this prototype system.