Nonnegative tensor-based linear dynamical systems for recognizing human action from 3D skeletons
Summary: Recently, skeleton-based action recognition has become a very important topic in the field of computer vision. It is a challenging task to accurately build a human action model and precisely distinguish similar human actions. In this paper, an action (skeleton sequence) is represented as a third-order nonnegative tensor time series to capture the original spatiotemporal information of the action. As a linear dynamical system (LDS) is an efficient tool for encoding the spatiotemporal data in various disciplines, this paper proposes a nonnegative tensor-based LDS (nLDS) to model the third-order nonnegative tensor time series. Nonnegative Tucker decomposition (NTD) is utilized to estimate the parameters of the nLDS model. These parameters are used to build extended observability sequence \(\mathbf{O}_{\infty}^T\) for the action, which implies that \(\mathbf{O}_{\infty}^T\) can be considered as the feature descriptor of the action. To avoid the limitations introduced by approximating \(\mathbf{O}_{\infty}^T\) with a finite-order matrix, we represent an action as a point on infinite Grassmann manifold comprising the orthonormalized extended observability sequences. The classification task can be performed by dictionary learning and sparse coding on the infinite Grassmann manifold. The experimental results on the MSR-Action3D, UTKinect-Action, and G3D-Gaming datasets demonstrate that the proposed approach achieves a better performance in comparison with the state-of-the-art methods.
- Key-skeleton-pattern mining on 3D skeletons represented by Lie group for action recognition
- Human gesture recognition on product manifolds
- Multi-derivative physical and geometric convolutional embedding networks for skeleton-based action recognition
- Action recognition based on spatio-temporal information and nonnegative component representation
- Rank-1 tensor projection via regularized regression for action classification
- Dynamic textures
- Efficient Nonnegative Tucker Decompositions: Algorithms and Uniqueness
- scientific article; zbMATH DE number 4213315 (Why is no real title available?)
- Schubert varieties and distances between subspaces of different dimensions
- The Geometry of Algorithms with Orthogonality Constraints
- The self-organizing map
- Key-skeleton-pattern mining on 3D skeletons represented by Lie group for action recognition
- Rank-1 tensor projection via regularized regression for action classification
- Human activity recognition based on 3D skeletons and an MCRF model
- Action recognition based on spatio-temporal information and nonnegative component representation
- Human gesture recognition on product manifolds
This page was built for publication: Nonnegative tensor-based linear dynamical systems for recognizing human action from 3D skeletons
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2298940)
