Persistent Homology of Attractors For Action Recognition [article]

Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga
2016 arXiv   pre-print
In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis. We model human actions using the topological features of the attractor of the dynamical system. We reconstruct the phase-space of time series corresponding to actions using time-delay embedding, and compute the persistent homology of the phase-space reconstruction. In order to better represent the topological properties of the phase-space, we
more » ... e the temporal adjacency information when computing the homology groups. The persistence of these homology groups encoded using persistence diagrams are used as features for the actions. Our experiments with action recognition using these features demonstrate that the proposed approach outperforms other baseline methods.
arXiv:1603.05310v1 fatcat:jiqfxspzancx7m3rqd7nvu4xnu