center for robotics and embedded systems University of Southern California Viterbi School of Engineering

We present an extension of Isomap nonlinear dimension reduction \cite{Tenenbaumetal2000} for data with both spatial and temporal relationships. Our method, ST-Isomap, augments the existing Isomap framework to consider temporal relationships in local neighborhoods that can be propagated globally via a shortest-path mechanism. Two instantiations of ST-Isomap are presented for sequentially continuous and segmented data. Results from applying ST-Isomap to real-world data collected from human motion performance and humanoid robot teleoperation are also presented.


Go Home
Maintained by webmaster