Compressive Sensing-based Target Tracking for Wireless Visual Sensor Networks

Limited storage, channel bandwidth, and battery lifetime are the main concerns when dealing with Wireless Visual Sensor Networks (WVSNs). Surveillance application for WVSNs is one of the important applications that requires high detection reliability and robust tracking, while minimizing the usage of energy as visual sensor nodes can be left for months without any human interaction. In surveillance applications, within WVSN, only single view target tracking is achieved to keep minimum number of visual sensor nodes in a ’wake-up’ state to optimize the use of nodes and save battery life time, which is limited in WVSNs. Least Mean square (LMS) adaptive filter is used for tracking to estimate target’s next location. Moreover, WVSNs retrieve large data sets such as video, and still images from the environment requiring high storage and high bandwidth for transmission which are limited. Hence, suitable representation of data is needed to achieve energy efficient wireless transmission and minimum storage. In this paper, the impact of CS is investigated in designing target detection and tracking techniques for WVSNs- based surveillance applications, without compromising the energy constraint which is one of the main characteristics of WVSNs. Results have shown that with compressive sensing (CS) up to 31 % measurements of data are required to be transmitted, while preserving the detection and tracking accuracy which is measured through comparing targets trajectory tracking