Extraction method of swimming trajectory for behavior analysis of medaka ()

Matsuda, Asahi*; Takahashi, Satoru*; Kawabata, Kuniaki   ; Oda, Shoji*; Kaneko, Shunichi*

In recent years, biology researchers elucidate the biological and behavioral mechanisms based on measurement of observation data. Then, it is accompanied with time cost and misrecognition to measure a trajectory of creature from observation data based on human eyes. Therefore, biology researchers require automated measurement and recording support system. In this paper, we introduce a new method of swimming trajectory generation for analyzing of medaka behavior. Then, in order to recognize medaka behavior a method which combines orientation code matching by rotation invariant multiple-templates and particle filter based on multiple-likelihood functions is introduced. Through experimentations we prove the effectiveness of our method.