Abstract. Approaches to visual navigation, e.g. used in robotics, require computationally efficient, numerically stable, and robust methods for the estimation of ego-motion. One of...
This paper presents a new approach for time series prediction using local dynamic modeling. The proposed method is composed of three blocks: a Time Delay Line that transforms the o...
Dynamic analysis of video sequences often relies on the segmentation of the sequence into regions of consistent motions. Approaching this problem requires a definition of which mo...
The dynamic texture (DT) is a probabilistic generative model, defined over space and time, that represents a video as the output of a linear dynamical system (LDS). The DT model ...
Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...