Persistent Homology of Attractors For Action Recognition
This work addresses action recognition for computer vision applications, but it appears incremental as it builds on existing topological data analysis methods.
The paper tackled action recognition from 3D motion capture data by modeling human actions using topological features of attractors in dynamical systems, and it demonstrated that the proposed approach outperforms baseline methods.
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 incorporate 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.