Classification of poses and movement phases

Authors:
Adam Świtoński;Henryk Josiński;Karol Jędrasiak;Andrzej Polański;Konrad Wojciechowski
Affiliations:
Polish-Japanese Institute of Information Technology, Bytom, Poland and Silesian University of Technology, Gliwice, Poland;Polish-Japanese Institute of Information Technology, Bytom, Poland and Silesian University of Technology, Gliwice, Poland;Polish-Japanese Institute of Information Technology, Bytom, Poland;Polish-Japanese Institute of Information Technology, Bytom, Poland and Silesian University of Technology, Gliwice, Poland;Polish-Japanese Institute of Information Technology, Bytom, Poland and Silesian University of Technology, Gliwice, Poland
Venue:
ICCVG'10 Proceedings of the 2010 international conference on Computer vision and graphics: Part I
Year:
2010

Citing 5
Cited 1

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Motion graphs

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Flexible automatic motion blending with registration curves

Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
A Model-Based Approach for Estimating Human 3D Poses in Static Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Application of a hybrid algorithm for non-humanoid skeleton model estimation from motion capture data

ICCVG'12 Proceedings of the 2012 international conference on Computer Vision and Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have focused on the problem of classification of motion frames representing different poses by supervised machine learning and dimensionality reduction techniques. We have extracted motion frames from global database manually, divided them into six different classes and applied classifiers to automatic pose type detection. We have used statistical Bayes, neural network, random forest and Kernel PCA classifiers with wide range of their parameters. We have tried classification on the original data frames and additional reduced their dimensionality by PCA and Kernel PCA methods. We have obtained satisfactory results rated in best case 100 percent of classifiers efficiency.