[1C4-J-3] Data mining: applications to images

[1C4-J-3-01] Body Motion Segmentation in Non-Human Primate Based on Gaussian Process Hidden Semi-Markov Model

〇Koki Mimura¹, Tomoaki Nakamura², Jumpei Matsumoto³, Hisao Nishijo³, Testuya Suhara¹, Daichi Mochihashi⁴, Takafumi Minamimoto¹ (1. National Institutes for Quantum and Radiological Science and Technology, 2. The University of Electro-Communications, 3. University of Toyama, 4. The Institute of Statistical Mathematics)

Keywords:body motion, dinamical segmentation, non-human primate, Gaussian process

Understanding the nature of nonverbal communication (eye contacts, face expressions, body postures, hand gestures, body motions, etc...) is one of the core issue in behavioral neuroscience. In this study, we demonstrated the data-driven dynamical segmentation of the body expressions in free moving small non-human primate, common marmoset. We developed a new marker-less 3D motion tracking system optimized to marmoset. Then, we proposed unsupervised segmentation using a Gaussian process-hidden semi-Markov model (GP-HSMM). As a result, we succeeded to classify three types of marmoset feeding behavior (high position feeding, low position feeding, and low position feeding with hands) only based on body parts positions, face direction, and body angle information. This result suggested that proposing system could represent high versatility to quantify the animal nonverbal body expressions without qualitative teacher labels.