A fundamental task in detecting foreground objects in both static and dynamic scenes is to take t... more A fundamental task in detecting foreground objects in both static and dynamic scenes is to take the best choice of color system representation and the efficient technique for background modeling. We propose in this paper a non-parametric algorithm dedicated to segment and to detect objects in color images issued from a football sports meeting. Indeed segmentation by pixel concern many
In this paper we present a new approach for tracking of human body in real video scenes, analyzin... more In this paper we present a new approach for tracking of human body in real video scenes, analyzing gestures and actions achieved by arms and legs and classifying global movements realized by the body. The detection and characterization of body in the different images of the sequence are achieved by using an image registration and a set of points of interest (POIs) issued from Harris corner detector. The tracking is achieved by template matching between POIs in a pair of consecutive frames in the sequence and is based on various distance calculation criteria. Gesture classification is done by the use of membership functions for angles realized by arms and legs. Movement analysis is made by an intelligent decision-making tool based on least squares method and model identification, able to estimate direction and orientation of body motion.
2010 4th International Symposium on Communications, Control and Signal Processing (ISCCSP), 2010
Abstract In this paper we develop an algorithm for robust model predictive control for Multi-Inpu... more Abstract In this paper we develop an algorithm for robust model predictive control for Multi-Inputs Multi-Outputs systems represented by the Generalized Orthonormal Basis Functions. A min-max optimization problem is reformulated and resolved by introducing techniques ...
A fundamental task in detecting foreground objects in both static and dynamic scenes is to take t... more A fundamental task in detecting foreground objects in both static and dynamic scenes is to take the best choice of color system representation and the efficient technique for background modeling. We propose in this paper a non-parametric algorithm dedicated to segment and to detect objects in color images issued from a football sports meeting. Indeed segmentation by pixel concern many
In this paper we present a new approach for tracking of human body in real video scenes, analyzin... more In this paper we present a new approach for tracking of human body in real video scenes, analyzing gestures and actions achieved by arms and legs and classifying global movements realized by the body. The detection and characterization of body in the different images of the sequence are achieved by using an image registration and a set of points of interest (POIs) issued from Harris corner detector. The tracking is achieved by template matching between POIs in a pair of consecutive frames in the sequence and is based on various distance calculation criteria. Gesture classification is done by the use of membership functions for angles realized by arms and legs. Movement analysis is made by an intelligent decision-making tool based on least squares method and model identification, able to estimate direction and orientation of body motion.
2010 4th International Symposium on Communications, Control and Signal Processing (ISCCSP), 2010
Abstract In this paper we develop an algorithm for robust model predictive control for Multi-Inpu... more Abstract In this paper we develop an algorithm for robust model predictive control for Multi-Inputs Multi-Outputs systems represented by the Generalized Orthonormal Basis Functions. A min-max optimization problem is reformulated and resolved by introducing techniques ...
Uploads
Papers