- "Covariance Tracker", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2006. ,
This video presents several object tracking results of a simple and elegant algorithm that can detect the non-rigid objects using a covariance based object description and an update mechanism based on means on Riemannian manifolds. We represent an object window as the covariance matrix of features as illustrated in Fig. 1, therefore we manage to capture the spatial and statistical properties as well as their correlation within the same representation. The covariance matrix enables efficient fusion of different types of features and modalities, and its dimensionality is small. We incorporated a model update algorithm using the elements of Riemannian geometry. The update mechanism effectively adapts to the undergoing object deformations and appearance changes. The covariance tracking method does not make any assumption on the measurement noise and the motion of the tracked objects, and provides the global optimal solution. We show in our technical paper  that it is capable of accurately detecting the non-rigid, moving objects in non-stationary camera sequences while achieving a promising detection rate of 97.4 percent.