We propose to model a tracked object in a video sequence by locating a list of object features that are ranked according to their\r\nability to differentiate against the image background. The Bayesian inference is utilised to derive the probabilistic location of the\r\nobject in the current frame, with the prior being approximated from the previous frame and the posterior achieved via the current\r\npixel distribution of the object. Consideration has also been made to a number of relevant aspects of object tracking including\r\nmultidimensional features and the mixture of colours, textures, and object motion. The experiment of the proposed method on\r\nthe video sequences has been conducted and has shown its effectiveness in capturing the target in a moving background and with\r\nnonrigid object motion.
Loading....