Abstract

Human detection and tracking is a primary focus for visual surveillance systems. However, current systems for human tracking are often complex and require vast amounts of computing resources. A reduction in complexity of the overall tracking system can be achieved by using a System of Systems (SoS) architecture. Once formed, a SoS architecture must achieve desirable levels of interoperability and integration. Proposed in this paper is a human tracking system that uses a net-centric SoS architecture capable of detecting a human via video surveillance and subsequently providing coordinates for mobile robot tracking. This SoS architecture establishes integration and conceptual interoperability through the standardization of communication and data representation. Within the SoS, communication is accomplished using a client-server architecture while data is structured according to a custom XML framework. The resulting SoS is composed of decentralized independent systems inter-operating on heterogeneous platforms to achieve the ultimate goal of human tracking.

Full Text
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