%0 Journal Article
	%A Insaf Ajili and  Malik Mallem and  Jean-Yves Didier
	%D 2018
	%J International Journal of Computer and Information Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 141, 2018
	%T Relevant LMA Features for Human Motion Recognition
	%U https://publications.waset.org/pdf/10009574
	%V 141
	%X Motion recognition from videos is actually a very
complex task due to the high variability of motions. This paper
describes the challenges of human motion recognition, especially
motion representation step with relevant features. Our descriptor
vector is inspired from Laban Movement Analysis method. We
propose discriminative features using the Random Forest algorithm
in order to remove redundant features and make learning algorithms
operate faster and more effectively. We validate our method on
MSRC-12 and UTKinect datasets.
	%P 792 - 796