Authors: Yafeng Liu,Shimin Feng,Zhikai Zhao,Enjie Ding
ArXiv: 1711.09511
Document:
PDF
DOI
Abstract URL: http://arxiv.org/abs/1711.09511v2
In this paper we propose the use of quantum genetic algorithm to optimize the
support vector machine (SVM) for human action recognition. The Microsoft Kinect
sensor can be used for skeleton tracking, which provides the joints' position
data. However, how to extract the motion features for representing the dynamics
of a human skeleton is still a challenge due to the complexity of human motion.
We present a highly efficient features extraction method for action
classification, that is, using the joint angles to represent a human skeleton
and calculating the variance of each angle during an action time window. Using
the proposed representation, we compared the human action classification
accuracy of two approaches, including the optimized SVM based on quantum
genetic algorithm and the conventional SVM with grid search. Experimental
results on the MSR-12 dataset show that the conventional SVM achieved an
accuracy of $ 93.85\% $. The proposed approach outperforms the conventional
method with an accuracy of $ 96.15\% $.