Tracking in Presence of Total Occlusion and Size Variation using Mean Shift and Kalman Filter
TypeCommunications avec actes
The classical mean shift algorithm for tracking in perfectly arranged conditions constitutes a good object tracking method. However, in the real environment it presents some limitations, especially under the presence of noise, objects with varying size, or occlusions. In order to deal with these problems, this paper proposes a reliable object tracking algorithm using mean shift and the Kalman filter, which was added to the traditional algorithm as a predictor when no reliable model of the object being tracked is found. Experimental work demonstrates that the proposed mean shift Kalman filter algorithm improves the tracking performance of the classical algorithms in complicated real scenarios. The results involve the tracking of an object in a gray level and in a color sequence, with varying size and in presence of total occlusion.
Fichier(s) constituant cette publication
Cette publication figure dans le(s) laboratoire(s) suivant(s)
Visualiser des documents liés par titre, auteur, créateur et sujet.
Navigation and interaction in a real-scale digital mock-up using natural language and user gesture MIRZAEI, Mohammad Ali; CHARDONNET, Jean-Rémy; MERIENNE, Frédéric; GENTY, Ariane (2014)This paper tries to demonstrate a very new real-scale 3D system and sum up some firsthand and cutting edge results concerning multi-modal navigation and interaction interfaces. This work is part of the CALLISTO-SARI ...
MIRZAEI, Mohammad Ali; CHARDONNET, Jean-Rémy; PERE, Christian; MERIENNE, Frédéric (2012)This paper focuses on the measurement and the mathematical definition of cognitive parameters of designing a navigation systembased on these parameters. The nausea level due to different velocities of a 3D scene, the user ...
MIRZAEI, Mohammad Ali; CHARDONNET, Jean-Rémy; PERE, Christian; MERIENNE, Frédéric (2012)3D systems due to its complicated electronical, mechanical and vision accessories have enormous degree of complexity both in design and evaluation. Navigation system usually plays an important role in most 3D ...
Visually Induced Motion Sickness Estimation and Prediction in Virtual Reality using Frequency Components Analysis of Postural Sway Signal CHARDONNET, Jean-Rémy; MIRZAEI, Mohammad Ali; MERIENNE, Frédéric (2015)The paper proposes a method for estimating and predicting visually induced motion sickness (VIMS) occurring in a navigation task in a 3D immersive virtual environment, by extracting features from the body postural sway ...
MIRZAEI, Mohammad Ali; MERIENNE, Frédéric; OLIVER, James H.; CHARDONNET, Jean-Rémy (Springer-Verlag, 2014)This paper presents a novel speak-to-VR virtual reality peripheral network (VRPN) server based on speech processing. The server uses a microphone array as a speech source and streams the results of the process through a ...