Human motion recognition with a convolution kernel

We address the problem of human motion recognition in this paper. The goal of human motion recognition is to recognize the type of motion recorded in a video clip, which consists of a set of temporarily ordered frames. By defining a Mercer kernel between two video clips directly, we propose in this paper a recognition strategy that can incorporate both the information of each individual frame and the temporal ordering between frames. Combining the proposed kernel with the support vector machine, which is one of the most effective classification paradigms, the resulting recognition strategy exhibits excellent performance over real data sets

[1]  David Haussler,et al.  Convolution kernels on discrete structures , 1999 .

[2]  Nigel Goddard,et al.  The Perception of Articulated Motion: Recognizing Moving Light Displays , 1992 .

[3]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[4]  Bernhard Schölkopf,et al.  Incorporating Invariances in Support Vector Learning Machines , 1996, ICANN.

[5]  W. Dittrich.  Action Categories and the Perception of Biological Motion , 1993, Perception.

[6]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[7]  Hava T. Siegelmann,et al.  Support Vector Clustering , 2002, J. Mach. Learn. Res..

[8]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[9]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Mubarak Shah,et al.  Matching motion trajectories using scale-space , 1993, Pattern Recognit..

[11]  Vladimir Pavlovic,et al.  Impact of dynamic model learning on classification of human motion , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[13]  Aaron F. Bobick,et al.  Recognition of human body motion using phase space constraints , 1995, Proceedings of IEEE International Conference on Computer Vision.

[14]  Harris Drucker,et al.  Comparison of learning algorithms for handwritten digit recognition , 1995 .

[15]  Jake K. Aggarwal,et al.  Human Motion Analysis: A Review , 1999, Comput. Vis. Image Underst..

[16]  James W. Davis,et al.  The representation and recognition of human movement using temporal templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Osama Masoud,et al.  A method for human action recognition , 2003, Image Vis. Comput..

[18]  Nello Cristianini,et al.  Classification using String Kernels , 2000 .

[19]  Michael J. Black,et al.  Parameterized Modeling and Recognition of Activities , 1999, Comput. Vis. Image Underst..

[20]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[21]  Larry S. Davis,et al.  3-D model-based tracking of humans in action: a multi-view approach , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  R. Nelson,et al.  Low level recognition of human motion (or how to get your man without finding his body parts) , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[23]  L. Davis,et al.  el-based tracking of humans in action: , 1996 .

[24]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[25]  Ralf Herbrich,et al.  Learning Kernel Classifiers: Theory and Algorithms , 2001 .

[26]  Christina S. Leslie,et al.  Fast String Kernels using Inexact Matching for Protein Sequences , 2004, J. Mach. Learn. Res..

[27]  Osama Masoud,et al.  Online motion classification using support vector machines , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[28]  Mohammed Yeasin,et al.  Towards a unified framework for tracking and analysis of human motion , 2001, Proceedings IEEE Workshop on Detection and Recognition of Events in Video.

[29]  Bernhard Schölkopf,et al.  Comparing support vector machines with Gaussian kernels to radial basis function classifiers , 1997, IEEE Trans. Signal Process..

[30]  Bernhard Schölkopf,et al.  Dynamic Alignment Kernels , 2000 .

[31]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[32]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[33]  C. Watkins.  Dynamic Alignment Kernels , 1999 .

[34]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[35]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[36]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[37]  Gang Xu,et al.  Understanding human motion patterns , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).