Human Action Classification Using SVM_2K Classifier on Motion Features
作者： Hongying Meng , Nick Pears , Chris Bailey
DOI: 10.1007/11848035_61
关键词:
摘要: In this paper, we study the human action classification problem based on motion features directly extracted from video. order to implement a fast system, select simple that can be obtained non-intensive computation. We also introduce new SVM_2K classifier achieve improved performance over standard SVM by combining two types of feature vector together. After learning, implemented very quickly because is linear classifier. Experimental results demonstrate method efficient and may used in real-time systems.
springer.com
springerlink.com参考文章(15)
Rémi Ronfard, Daniel Weinland, Edmond Boyer, Motion History Volumes for Free Viewpoint Action Recognition Workshop on modeling People and Human Interaction (PHI'05). ,(2005)
Nello Cristianini, John Shawe-Taylor, Kernel Methods for Pattern Analysis ,(2004)
Hongying Meng, John Shawe-Taylor, Sandor Szedmak, Jason D. R. Farquhar, Support Vector Machine to Synthesise Kernels Lecture Notes in Computer Science. pp. 242- 255 ,(2005) , 10.1007/11559887_15
Nello Cristianini, John Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods ,(2000)
Shu-Fai Wong, Roberto Cipolla, Real-Time Adaptive Hand Motion Recognition Using a Sparse Bayesian Classifier Computer Vision in Human-Computer Interaction. pp. 170- 179 ,(2005) , 10.1007/11573425_17
Peter Sollich, Christopher K. I. Williams, Understanding Gaussian Process Regression Using the Equivalent Kernel Lecture Notes in Computer Science. pp. 211- 228 ,(2005) , 10.1007/11559887_13
J.K. Aggarwal, Q. Cai, Human Motion Analysis Computer Vision and Image Understanding. ,vol. 73, pp. 428- 440 ,(1999) , 10.1006/CVIU.1998.0744
S.-F. Wong, R. Cipolla, Real-time interpretation of hand motions using a sparse Bayesian classifier on motion gradient orientation images british machine vision conference. ,(2005) , 10.5244/C.19.41
C. Schuldt, I. Laptev, B. Caputo, Recognizing human actions: a local SVM approach international conference on pattern recognition. ,vol. 3, pp. 32- 36 ,(2004) , 10.1109/ICPR.2004.747
T. OGATA, High-Speed Human Motion Recognition Based on a Motion History Image and an Eigenspace The IEICE transactions on information and systems. ,vol. 89, pp. 281- 289 ,(2006) , 10.1093/IETISY/E89-D.1.281