International audienceIn this paper we propose a novel human action recognition method, robust to viewpoint variation, which combines skeleton-and depth-based action recognition approaches. For this matter, we first build several base classifiers, to independently predict the action performed by a subject. Then, two efficient combination strategies , that take into account skeleton accuracy and human body orientation, are proposed. The first is based on fuzzy switcher where the second uses a combination between fuzzy switcher and aggregation. Moreover, we introduce a new algorithm for the estimation of human body orientation. To perform the test we have created a new Multiview 3D Action public dataset with three viewpoint angles (30°,0°,-30°). The experimental results show that an efficient combination strategy of base classifiers improves the accuracy and the computational efficiency for human action recognition
Controlling multi-DOF (Degree of Freedom) micropositioning systems always represents great challenge because of the high sensitivity to the environment at this scale and the cross-coupling effects present between the different axes. A robust Luenberger observer-based state feedback design using interval analysis and regional pole assignment technique are introduced to control such systems. This robust control design keeps the same structure of the classical state-feedback with the usual Luenberger observer. However, the synthesises of the observer and the feedback controller are performed by means of interval techniques to find the set of gains that are robust against system uncertainties and that satisfy some predefined performances. For this matter, an algorithm based on Set Inversion Via Interval Analysis (SIVIA) combined with interval eigenvalues computation is proposed to find these robust gains. The control approach is validated in simulation and then tested experimentally to control a multi-DOF positioning structure.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.