Regression Based Trajectory Learning and Prediction for Human Motion

Abstract

This paper presents a method for learning and predicting human motion in closed environments. Many surveillance, security, entertainment and smart-home systems require the localization of human subjects and the prediction of their future locations in the environment. Traditional tracking methods employ a linear motion model for human motion. However, for complex scenarios, where motion trajectory is dependent on the structure of the environment, linear motion model is insufficient. In this paper, we present a behavior-aware method for learning and predicting human motion in closed environments. Our method adaptively combines traditional linear motion model, where there is not much behavioral data, with the learned motion model, where there is sufficient data available. We present the mathematical and implementation details along with the experimental results to show the effectiveness of our method.