Visual tracking using the Earth Mover's Distance between Gaussian mixtures and Kalman filtering

In this paper, we demonstrate how the differential Earth Mover's Distance (EMD) may be used for visual tracking in synergy with Gaussian mixtures models (GMM). According to our model, motion between adjacent frames results in variations of the mixing proportions of the Gaussian components representing the object to be tracked. These variations are computed in closed form by minimizing the differential EMD between Gaussian mixtures, yielding a very fast algorithm with high accuracy, without recurring to the EM algorithm in each frame. Moreover, we also propose a framework to handle occlusions, where the prediction for the object's location is forwarded to an adaptive Kalman filter whose parameters are estimated on line by the motion model already observed. Experimental results show significant improvement in tracking performance in the presence of occlusion.

Graphical AbstractFigure optionsDownload high-quality image (128 K)Download as PowerPoint slideResearch Highlights
► The differential earth mover's distance (DEMD) is used for visual tracking in synergy with Gaussian mixture models (GMM).
► Occlusions are handles by an adaptive Kalman filter whose state matrix changes over time according to the quality of the observation.
► Expirimental comparison between the proposed method, standard DEMD and mean shift.