Hybrid tracking approach for assistive environments

Camera based supervision is a critical component for patient monitoring in assistive environments. However, visual tracking still remains one of the biggest challenges in the area computer vision although it has been extensively studied during the previous decades. It this paper we propose a hybrid Rao -- Blackwellzed particle filter that combines two efficient, well-known tracking techniques with an innovative color observation representation method in order to improve the overall tracking performance. This representation is combined with color and edge representation to obtain improved tracking efficiency. Furthermore, the global edge description template for the edge representation (histogram of oriented gradients) was obtained using a machine learning technique. Initial experiments show that the principle behind the proposed algorithm is sound, yielding good results and thus allowing its adoption as an initial stage for patient behavior recognition.