Optimal joint selection for skeletal data from RGB-D devices using a genetic algorithm

Authors:
Pau Climent-Pérez;Alexandros Andre Chaaraoui;Jose Ramón Padilla-López;Francisco Flórez-Revuelta
Affiliations:
Department of Computer Technology, University of Alicante, Alicante, Spain;Department of Computer Technology, University of Alicante, Alicante, Spain;Department of Computer Technology, University of Alicante, Alicante, Spain;Faculty of Science, Engineering and Computing, Kingston University, Kingston upon Thames, United Kingdom
Venue:
MICAI'12 Proceedings of the 11th Mexican international conference on Advances in Computational Intelligence - Volume Part II
Year:
2012

Citing 9
Cited 0

Detection and Recognition of Periodic, Nonrigid Motion

International Journal of Computer Vision
Feature Selection for Knowledge Discovery and Data Mining

Feature Selection for Knowledge Discovery and Data Mining
Feature Subset Selection Using a Genetic Algorithm

IEEE Intelligent Systems
Further Research on Feature Selection and Classification Using Genetic Algorithms

Proceedings of the 5th International Conference on Genetic Algorithms
Different metaheuristic strategies to solve the feature selection problem

Pattern Recognition Letters
The feature selection problem: traditional methods and a new algorithm

AAAI'92 Proceedings of the tenth national conference on Artificial intelligence
Real-time classification of dance gestures from skeleton animation

SCA '11 Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation
Mining actionlet ensemble for action recognition with depth cameras

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
An efficient approach for multi-view human action recognition based on bag-of-key-poses

HBU'12 Proceedings of the Third international conference on Human Behavior Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

The growth in interest in RGB-D devices (e.g. Microsoft Kinect or ASUS Xtion Pro) is based on their low price, as well as the wide range of possible applications. These devices can provide skeletal data consisting of 3D position, as well as orientation data, which can be further used for pose or action recognition. Data for 15 or 20 joints can be retrieved, depending on the libraries used. Recently, many datasets have been made available which allow the comparison of different action recognition approaches for diverse applications (e.g. gaming, Ambient-Assisted Living, etc.). In this work, a genetic algorithm is used to determine the contribution of each of the skeleton's joints to the accuracy of an action recognition algorithm, thus using or ignoring the data from each joint depending on its relevance. The proposed method has been validated using a k-means-based action recognition approach and using the MSR-Action3D dataset for test. Results show the presented algorithm is able to improve the recognition rates while reducing the feature size.