Dependable cascading target tracking in heterogeneous mobile camera sensor networks

Abstract

Recent years have witnessed the development of Camera Sensor Networks (CSNs), but most of existing researches are based on homogeneous CSNs, which are expensive for the transition from traditional Wireless Sensor Networks (WSNs). In this paper, we focus on the target tracking problem in Heterogeneous Mobile Camera Sensor Networks (HMCSNs) which consists of a large number of static common sensors and a small number of mobile camera sensors. The objective is to track the target dependably with maximized effective monitoring time and short moving distance. A novel tracking algorithm is proposed where multiple camera sensors cooperate with each other to track the target in a cascading scheme. It improves the effective monitoring time and shortens the moving distance of cameras. Moreover, the dependability is also improved even if the prediction about the target is not accurate. The effectiveness of the proposed algorithm is validated by simulation results, which show high monitoring ratio and comparatively short moving distance.