Market-Based Framework for Mobile Surveillance Systems

The active surveillance of public and private sites is increasingly becoming a very important and critical issue. It is therefore, imperative to develop mobile surveillance systems to protect these sites. Modern surveillance systems encompass spatially distributed mobile and static sensors in order to provide effective monitoring of persistent and transient objects and events in a given Area Of Interest (AOI). Mobile sensors have emerged as a solution to overcome the limitations of the static sensors. Mobile sensors are capable of sensing, processing, moving and communicating with other nodes. They can sample the environment at different locations, exchange information with other nodes, and collaboratively accomplish the required mission. Mobile surveillance systems incorporate self-organized networks of mobile sensing nodes of different modalities, data and information fusion nodes, acting nodes and control nodes. These self-organized nodes can collaboratively and continuously sense within the volume of interest, as well as physically manipulate and interact with it. These surveillance systems provide systematic observation of an AOI that includes the timely detection, localization, recognition and identification of objects and events, their relationships, activities, and plans, in order to determine whether they are behaving normally, or whether there is any deviation from their expected behavior. To achieve this complete situation awareness, the system starts by collecting the relevant data in order to identify situation entities and their relationships. Then the system performs a relational analysis of object-events, followed by intent estimation and consequence prediction. The realization of the potential of mobile surveillance requires the solution of different challenging problems such as task allocation, mobile sensor deployment, multisensor management, cooperative object detection and tracking, decentralized data fusion, and interoperability and accessibility of system nodes. This thesis proposes a market-based framework that can be used to handle different problems of mobile surveillance systems. Task allocation and cooperative target-tracking iii are studied using the proposed framework as two challenging problems of mobile surveillance systems. These challenges are addressed individually and collectively. Although a great number of task allocation approaches have been reported in the literature, many aspects have to date been given only sparse attention. Examples of these aspects are complex task allocation and constrained task allocation. The developed surveillance framework in this thesis addresses complex task allocation that uses task tree structure. Hierarchical and centralized complex task allocation algorithms are presented to allocate a set of complex tasks to a mobile sensor team. Besides complex task allocation, the cooperative target tracking problem is also tackled in this thesis. The proposed cooperative tracking approach is inspired by market-based economic systems. In the proposed framework, mobile sensors are self-interested agents with the primary goal of maximizing individuals’ profits. The presented methodology inherits the flexibility of markets in allowing cooperation and competition to emerge opportunistically among the agents. These agents implement an Extended Kohonen Maps-based algorithm for target tracking. Two versions of the Extended Kohonen Maps are proposed: supervised, and unsupervised. A hybrid clustering technique is used to decrease the number of active trackers during tracking, and thus save energy.