Millimeter wave signals and large antenna arrays are considered enabling technologies for future 5G networks. Despite their benefits for achieving high data rate communications, their potential advantages for tracking of the location of the user terminals are largely undiscovered. In this paper, we propose a novel support detection-based channel training method for frequency selective millimeter-wave (mm-wave) multiple-input-multiple-output system with lens antenna arrays. We show that accurate position and orientation estimation and tracking is possible using signals from a single transmitter with lens antenna arrays. Particularly, the beamspace channel estimation is formulated as two sparse signal recovery problems in the downlink and uplink for the estimation of angle-of-arrival, angle-of-departure, and time-of-arrival. The proposed method offers a higher sparse detection probability compared to the compressed sensing based solutions. Finally, a joint heuristic beamformer design and user position and orientation tracking approach are proposed based on initial estimation of channel parameters obtained in the training phase.