Title :
A gesture expressive model based on Laban qualities
Author :
Truong, Arthur ; Boujut, Hugo ; Zaharia, Titus
Author_Institution :
ARTEMIS Dept., Inst. Mines-Telecom, Evry, France
Abstract :
Today, gesture analysis lacks of global models able to characterize motion expressivity and its communicational character. In this paper, we propose a set of new gesture descriptors inspired from Laban Movement Analysis (LMA) and based on 3D body trajectories. We test our descriptors ability to characterize human actions in a machine learning framework (with SVM and different random forest techniques). The results obtained on Microsoft Research Cambridge-12 (MSRC-12) dataset and show very high recognition rates (more than 97%).
Keywords :
gesture recognition; image motion analysis; learning (artificial intelligence); support vector machines; 3D body trajectories; LMA; Laban Movement Analysis; Laban qualities; Microsoft Research Cambridge-12 dataset; SVM; gesture descriptors; gesture expressive model; human action characterization; machine learning framework; random forest techniques; recognition rates; Analytical models; Conferences; Gesture recognition; Hidden Markov models; Joints; Shape; Trajectory; Gesture expressivity; Laban movement analysis; gesture recognition; machine learning; motion features;
Conference_Titel :
Consumer Electronics ??? Berlin (ICCE-Berlin), 2014 IEEE Fourth International Conference on
Conference_Location :
Berlin
DOI :
10.1109/ICCE-Berlin.2014.7034309
