The nature of statistical learning theory
The nature of statistical learning theory
Recognition of human body motion using phase space constraints
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
View Invariance for Human Action Recognition
International Journal of Computer Vision
Nonlinear Time Series Analysis
Nonlinear Time Series Analysis
Optimization and Filtering for Human Motion Capture
International Journal of Computer Vision
The i3DPost Multi-View and 3D Human Action/Interaction Database
CVMP '09 Proceedings of the 2009 Conference for Visual Media Production
A survey on vision-based human action recognition
Image and Vision Computing
Human motion recognition using Isomap and dynamic time warping
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Skeleton and shape adjustment and tracking in multicamera environments
AMDO'10 Proceedings of the 6th international conference on Articulated motion and deformable objects
Temporal Extension of Laplacian Eigenmaps for Unsupervised Dimensionality Reduction of Time Series
ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
3D human action recognition using spatio-temporal motion templates
ICCV'05 Proceedings of the 2005 international conference on Computer Vision in Human-Computer Interaction
Real-time human pose recognition in parts from single depth images
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Machine Recognition of Human Activities: A Survey
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
This paper presents a human action recognition framework based on the theory of nonlinear dynamical systems. The ultimate aim of our method is to recognize actions from multi-view video. We estimate and represent human motion by means of a virtual skeleton model providing the basis for a view-invariant representation of human actions. Actions are modeled as a set of weighted dynamical systems associated to different model variables. We use time-delay embeddings on the time series resulting of the evolution of model variables along time to reconstruct phase portraits of appropriate dimensions. These phase portraits characterize the underlying dynamical systems. We propose a distance to compare trajectories within the reconstructed phase portraits. These distances are used to train SVM models for action recognition. Additionally, we propose an efficient method to learn a set of weights reflecting the discriminative power of a given model variable in a given action class. Our approach presents a good behavior on noisy data, even in cases where action sequences last just for a few frames. Experiments with marker-based and markerless motion capture data show the effectiveness of the proposed method. To the best of our knowledge, this contribution is the first to apply time-delay embeddings on data obtained from multi-view video.