Motion Prediction of Regions Through the Statistical Temporal Analysis Using an Autoregressive Moving Average (ARMA) Model
Angel Sanchez Garcia, Homero Vladimir Ríos-Figueroa, Maria De Lourdes Velasco Vasquez, Gerardo Contreras Vega, Antonio Marı́n-Hernández · Research in Computing Science · 2014
Currently many applications require tracking moving objects, and that information is used to plan the path of motion or change according to the position of a visual target [1] [2].Computer vision systems can predict the motion of objects if the movement behavior is analyzed over time, ie, it is possible to find out future values based on previously observed values.In this paper, a proposal to predict motion of segmented regions is presented, through an analysis of a time series using an ARMA model.Two scenarios with different characteristics are presented as test cases.Segmentation of moving objects is done through the clustering of optical flow vectors for similarity, which are obtained by Pyramid Lucas and Kanade algorithm.