Activity Recognition via Feature Decomposition

Qing Wei; Hao Zhang; Zhi Jing Liu

doi:10.4028/www.scientific.net/AMR.243-249.6221

Paper Titles

Numerical Simulation of Progressive Collapse and Study of Resisting Progressive Collapse of Spatial Grid Structures Based on ANSYS/LS-DYNA
p.6202

Numerical Simulation of Earth-Contact Heat Transfer
p.6206

Improvement Method about Design Norms’ Implementation Based on AutoCAD 2007
p.6212

Comparative Analysis between Dynamic Simulation and Practical Result of Demolition of Building Structures by Blasting
p.6216

Activity Recognition via Feature Decomposition
p.6221

Global Bifurcation of a Tuning Mass Damper with Plastic Impacts
p.6225

Numerical Simulation of Ship-bridge Collision Based on LS-DYNA Technique
p.6230

Exploration Method for Extra Heavy Oil Reservoir with Top Water
p.6237

The FEM Analysis and Optimization Design of Main Beam of Horizontal Directional Drilling
p.6241

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 243-249Activity Recognition via Feature Decomposition

Activity Recognition via Feature Decomposition

Abstract:

This paper presents a new recognition method for human motion, which is represented by Haar wavelet transform and recognized by Coupled Hidden Markov Model. We tackle the challenge of detecting the feature points by Haar wavelet transform to improve the accuracy. We extract binary silhouette after creating the background model. Then the low-level features are detected by Haar wavelet and principal vectors in two subspaces are obtained. We utilize Coupled Hidden Markov Models to model and recognize them, and demonstrate their usability. Compared with others, our approach is simple and effective in feature detection, strength in robustness. Therefore, the video surveillance based on our method is practicable in (but not limited to) many scenarios where the background is known.

You might also be interested in these eBooks

Advances in Civil Engineering and Architecture

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 243-249)

Pages:

6221-6224

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.243-249.6221

Citation:

Cite this paper

Online since:

May 2011

Authors:

Qing Wei, Hao Zhang, Zhi Jing Liu

Keywords:

Activity Recognition, Feature Decomposition, Key Point, Wavelet Transform (WT)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] H. Zhang, Z. Liu and H. Zhao, "Contour Extraction of Human with Single-pixel Width," Applied Mechanics and Materials, vol. 20-23, pp.376-381, 2010.

DOI: 10.4028/www.scientific.net/amm.20-23.376

Google Scholar

[2] Haar Alfred, Zur Theorie der orthogonalen Funktionensysteme, (German) Mathematische Annalen, vol. 69, no. 3, pp.331-371, 1910.

DOI: 10.1007/bf01456326

Google Scholar

[3] H. Zhang and Z. Liu, "Gait Representation and Recognition Using Haar Wavelet and Radon Transform," 2009 WASE International Conference on Information Engineering, vol. 1, pp.83-86, 2009.

DOI: 10.1109/icie.2009.102

Google Scholar

[4] M. A. Mendoza and N. P. De La Blanca, "Applying Space State Models in Human Action Recognition: A comparative Study," Lecture Notes in Computer Science, vol. 5098LNCS, pp.53-62, 2008.

DOI: 10.1007/978-3-540-70517-8_6

Google Scholar

[5] H. Zhang, Z. Liu, Q. Wei, H. Zhao, and W. Wang, "Classifying human activities using feature points," International Conference on Image Processing and Pattern Recognition in Industrial Engineering, vol. 7820, pp. 78203S, 2010.

DOI: 10.1117/12.867443

Google Scholar