A location-tracking testbed using vision-assisted scheme for wireless sensor networks

This paper presents the performance of an efficient location tracking algorithm based on Alpha-Beta (α-β) filtering with visionassisted in a wireless sensor network (WSN) environment. With a vision-assisted calibration technique based on normalized crosscorrelation scheme, the proposed approach is an accuracy enhancement procedure that effectively removes system errors causing uncertainty in measuring a dynamic environment. That is, using the vision-assisted approach to estimate the locations of the reference nodes as landmarks, an α-β tracking scheme with the landmark information can calibrate the location estimation and improve the corner effect. The experimental results demonstrate that the proposed location-tracking algorithm combining visionassisted scheme with α-β filtering approach can achieve an accurate location very close to the traditional Kalman filtering (KF) algorithm in a ZigBee positioning platform. As compared with the KF-based approach, the proposed tracking approach can avoid repeatedly calculating the Kalman gain and achieve reasonably good performance with much lower computational complexity.