Time-Series Human Motion Analysis with Kernels Derived from Learned Switching Linear Dynamics

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we propose a novel kernel computation algorithm between time-series human motion data for online action recognition. The proposed kernel is based on probabilistic models called switching linear dynamics (SLDs). SLD is one of the powerful tools for tracking, analyzing and classifying human complex time-series motion. The proposed kernel incorporates information about the latent variables in SLDs. The empirical evaluation using real motion data shows that a classifier using SVM with our proposed kernel has much better performance than the classifiers with some conventional kernel techniques. Another experimental result using kernel principal component analysis shows that the proposed kernel has excellent performance in extracting and separating different action categories, such as walking and running.

著者

• MORI Taketoshi

  The University of Tokyo

• SHIMOSAKA Masamichi

  The University of Tokyo

• HARADA Tatsuya

  The University of Tokyo

• SATO Tomomasa

  The University of Tokyo

関連論文

• Time-Series Human Motion Analysis with Kernels Derived from Learned Switching Linear Dynamics
• Time-Series Human Motion Analysis with Kernels Derived from Learned Switching Linear Dynamics
• 1A1-K13 On the Stable Caging of Convex Objects with Least Fingers and Boundary Clouds(New Control Theory and Motion Control)

スポンサーリンク