Recognition of human body motion using phase space constraints
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Recognizing Human Actions: A Local SVM Approach
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Space-Time Behavior Based Correlation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Actions Sketch: A Novel Action Representation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
View Invariance for Human Action Recognition
International Journal of Computer Vision
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words
International Journal of Computer Vision
Recovering human body configurations: combining segmentation and recognition
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Hi-index | 0.00 |
This paper presents some interesting features that are revealed from the trajectories of human motions such as walk, run, and jump. Each trajectory represents a chaotic time series. The phase space that exhibits a characteristic trajectory representing the regularity of the time series is reconstructed by using appropriate time delay and dimension. Self organizing map (SOM) with neural network is used to visualize the underlying characteristics of a motion. The analysis of time series with different motions has revealed that the classification of a particular motion is possible from the orientation of phase space and SOM. In addition, correlation dimensions (CDs) are computed to quantify the regularity of a time series. Since computing the overall complexity of body points such as head, two hands and two legs is important, `CD triangle' is introduced first time. This is useful in classifying human body points.