| |
Description
Target tracking in over a small-scale area using wireless sensor networks (WSNs) is a technique that can be used in applications ranging from emergency rescue after an earthquake to security protection in a building. Many target tracking systems rely on the presence of an electric device which must be carried by the target in order to reports back its location and status. This makes these systems unsuitable for many emergency applications; in such applications tracking systems that where no devices are attached to the targets are needed. Radio-Frequency (RF) tomographic tracking is one such device-free tracking technique. This system tracks moving targets by analyzing changes in attenuation in wireless transmissions. The target can be tracked within the sensor network area without being required to carry an electric device.
In this research project, we propose a novel sequential Monte Carlo (SMC) algorithm for RF tomographic tracking. Currently it can track a single target moving in a wireless sensor network without the system needing to be trained (please see the video in project page). The algorithm adopts a particle filtering method[1] to estimate the target position and incorporates on-line Expectation Maximization (EM)[2] to estimate model parameters. Based on experimental measurements, the work also introduces a novel measurement model for the attenuation caused by a target with the goal of improving estimation accuracy. The performance of the algorithm is assessed through numerical Matlab simulations and field experiments carried out with a wireless sensor network testbed (using more than 24 TelosB sensor nodes). Our goal is to achieve real-time multiple targets tracking in both indoor and outdoor complex environments using wireless sensor networks.
References
[1] A. Doucet and M. Johansen. A tutorial on particle filtering and smoothing:
fifteen years later. In Oxford Handbook of Nonlinear Filtering, pp.
656-704. Oxford Univ. Press, 2011.
[2] C. Andrieu, A. Doucet, and V.B. Tadic.
On-line parameter estimation in general state-space models. In Proc. IEEE Conf. Decision and Control/European Control Conf.
pp. 332-337, Seville, Spain, Dec. 2005.
Publications
[1] Y.P. Li*, X. Chen*, M.J. Coates, B. Yang, Sequential Monte Carlo Radio-Frequency Tomographic Tracking, in Proc. Intl. Conf. Acoustics, Speech, and Signal Processing (ICASSP), to appear, May 2011. *Equal first-authors.
available at here.
[2] X. Chen, A. Edelstein, Y.P. Li, M.J. Coates, M. Rabbat, A.D. Men, Sequential Monte Carlo for Simultaneous Passive Device-Free Tracking and Sensor Localization Using Received Signal Strength Measurements, in Proc. ACM/IEEE Intl. Conf. Information Processing in Sensor Networks (IPSN), to appear, Apr. 2011.
available at here.
|
Return to RF Tomographic Tracking Project