Real-timeVideoSegmentation Using Student'stMixture Model

Mixture models for video segmentation have mainly revolved around Gaussian distributions for a long time due to their simplicity and applicability. In thiswork, we proposeanovel real-time video segmentation algorithm based on Student's t mixture model. Though, Student's t-distribution has been used for image segmentation by applying Expectation Maximization(EM) algorithm,the same technique cannotbe followedin videosegmentationduetoexceptional increase in computational complexity. Thus,in spiteof beinga more heavily-tailed distribution comparedto Gaussian, Student's t mixture model remained unexplored for video segmentation. In this work, a novel and effective recursive lter based formulation has been introduced to update the mixture model with new observations. Our analysis and experimental results show that real-time, robust and improved video segmentation canbe performed using Student'stmixture model compared to the conventional mixture models