Object Modelling in Videos via Multidimensional Features of Colours and Textures

We propose to model a tracked object in a video sequence by locating a list of object features that are ranked according to their ability to differentiate against the image background. The Bayesian inference is utilised to derive the probabilistic location of the object in the current frame, with the prior being approximated from the pervious frame and the posterior achieved via the current pixel distribution of the object. The experiment of the proposed method on the video sequences has also been conducted and has shown its effectiveness in capturing the target in a moving background and with non-rigid object motion.