Subject-independent natural action recognition
Haibing Ren, Guangyou Xu, Seok-Cheol Kee · 2004
A primitive-based dynamic Bayesian networks are proposed for subject-independent natural action recognition. Inferred by high-level knowledge, primitives are distinctive features that describe the context information and the motion information representing human action as well as pose. Dynamic Bayesian networks could fuse multi-information so that many kinds of weak information could function as strong information for inference. The experimental results show that primitive-based dynamic Bayesian networks not only increase the recognition rate but also improve the robustness.