Intelligent target tracking in Wireless Visual Sensor Networks

In this paper, a new target tracking method is proposed in Wireless Visual Sensor Networks (WVSN) using target movement prediction. Two important criteria in this regard are accuracy of tracking and efficient energy consumption. Because there is a direct relationship between the amount of coverage and accuracy tracking, an Evolutionary Algorithm (EA) is used as pre-processing to increase the coverage percentage. Then, a neural network-based approach using history of target movements is presented to predict the path of the target. Computer simulations showed improvement in tracking accuracy, configuration of WVSN cost and energy conservation. The important advantage of this approach is the capability of tracking in an environment, which is not covered completely.