Human Action Recognition Using Tensor Dynamical System Modeling

Chan-Su Lee; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 21-25

Abstract


This paper presents a new framework for human action classification using a tensor dynamical model of human action from 3-dimensional (3D) volume sequences and distance measurement on Grassmann manifold . The tensor dynamical model is an extension of linear dynamical models for multi-dimensional sequence analysis. Each subdimensional linear dynamic models are estimated from tensor sequences using an iterative expectation-maximization (EM) algorithm after projection of tensor sequence to each dimensional axis. The combination of distances on Grassmann manifold of linear dynamic systems in each dimension of the tensor dynamic model provides similarity measurement between two tensor dynamical systems. The proposed approach can be applied to 3D depth or convex hull data as well as 2D video image sequences. Experimental results show good performance in human action recognition from INRIA multiview human action database.

Related Material


[pdf]
[bibtex]
@InProceedings{Lee_2017_CVPR_Workshops,
author = {Lee, Chan-Su},
title = {Human Action Recognition Using Tensor Dynamical System Modeling},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}