Abstract
In this paper, we propose an effective and robust decentralized tracking scheme based on the square root cubature information filter (SRCIF) to balance the energy consumption and tracking accuracy in wireless camera sensor networks (WCNs). More specifically, regarding the characteristics and constraints of camera nodes in WCNs, some special mechanisms are put forward and integrated in this tracking scheme. First, a decentralized tracking approach is adopted so that the tracking can be implemented energy-efficiently and steadily. Subsequently, task cluster nodes are dynamically selected by adopting a greedy on-line decision approach based on the defined contribution decision (CD) considering the limited energy of camera nodes. Additionally, we design an efficient cluster head (CH) selection mechanism that casts such selection problem as an optimization problem based on the remaining energy and distance-to-target. Finally, we also perform analysis on the target detection probability when selecting the task cluster nodes and their CH, owing to the directional sensing and observation limitations in field of view (FOV) of camera nodes in WCNs. From simulation results, the proposed tracking scheme shows an obvious improvement in balancing the energy consumption and tracking accuracy over the existing methods.
Highlights
Among many surveillance functions of Wireless Sensor Networks (WSNs), tracking a moving target in a sensing field is a major one that has wide-spread areas of applications, such as habitat monitoring, traffic monitoring, and intruder tracking [1,2,3]
This paper focuses on balancing energy consumption and tracking accuracy in single target tracking in dense wireless camera sensor networks (WCNs)
The cluster head (CH) activates or deactivates a camera analyzing the usefulness of its measurements and the resources as given in [23], which adopts an on-line decision making approach that maximizes the trade-off between sensing gain and resource consumption
Summary
Among many surveillance functions of Wireless Sensor Networks (WSNs), tracking a moving target in a sensing field is a major one that has wide-spread areas of applications, such as habitat monitoring, traffic monitoring, and intruder tracking [1,2,3]. The current presence of moving targets will be detected by sampling the sensed signals (e.g., light, sound, image, or video) [4]. A new trend in target tracking is to deploy sensor nodes with smart cameras to capture, process and analyze image data locally and to send extracted information back to the sink node [7]. The target tracking in WCNs is greatly different from that in traditional WSNs with respect to camera field of view (FOV), bandwidth consumption, and multimedia data processing [8]. Much attention should be paid to some special target tracking schemes in WCNs
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call