Abstract
With rapid advancements in MEMS technologies, sensor networks have made possible a broad range of applications in real time. Object tracking and detection is one of the most prominent applications for wireless sensor networks. Individual object tracking and detection has been intensively discussed, such as tracking enemy vehicles and detecting illegal border crossings. The tracking and detection of continuous objects such as fire smoke, nuclear explosions and hazardous bio-chemical material diffusions pose new challenges because of the characteristics of such objects, i.e., expanding and shrinking in size, changing in shape, splitting into multiple objects or merging multiple objects into one over time. A continuous object covers a large area over the network and requires extensive communication to detect and track. Tracking continuous objects accurately and efficiently is challenging, whereas extensive communication consumes massive energy in the network, and handling energy in wireless sensor network (WSNs) is a key issue in prolonging the lifetime of a network.
In this paper, we propose collaborative boundary detection and tracking of continuous objects in WSNs. The proposed scheme adopts local communication between sensor nodes for the purpose of finding boundary nodes; boundary nodes enhance energy efficiency. The scheme uses an interpolation algorithm to find the boundary points and to acquire a precise boundary shape for the continuous object. The proposed scheme not only improves the tracking accuracy but also decreases energy consumption by reducing the number of nodes that participate in tracking and minimizing the communications cost. Simulation results show a significant improvement over the existing solutions.