A positioning scheme combining Kalman filtering with vision assisting for wireless sensor networks

This paper presents the performance of an adaptive location estimator combining Kalman filtering (KF) scheme with vision-assisted scheme for wireless sensor networks. To improve the location accuracy, a KF tracking scheme is employed at a mobile terminal to track variations of the location estimate. In addition, with a vision-assisted calibration technique based on the normalized cross-correlation scheme, the proposed approach is an accuracy enhancement procedure that effectively removes system errors causing uncertainty in measuring a dynamic environment. Therefore, using the vision-assisted approach to estimate the locations of the reference nodes as landmarks, a KF-based scheme with the landmark information can calibrate the location estimation and improve the corner effect. The experimental results demonstrate that more than 60 percent of the location estimates computed from the proposed approach have error distances less than 1.4 meters in a ZigBee positioning platform. As compared with the non-tracking algorithm and non-vision-assisted approach, the proposed algorithm can achieve reasonably good performance.