Distributed Multitarget Tracking and Identity Management

The problem of tracking multiple targets and managing their identities in sensor networks is considered. Each sensor is assumed to have its own surveillance region and an ability to communicate with its neighboring sensors.We propose a scalable, distributed, multitarget-tracking and identity-management algorithm that can track an unknown number of targets and manage their identities efficiently in a distributed sensor network environment. Distributed multitarget tracking and identity management finds a globally consistent solution by maintaining local consistency among neighboring sensors. Distributed multitarget tracking and identity management consists of data association, multitarget tracking, identity management, and identity and track fusion. The data-association and multitarget-tracking problems are efficiently solved byMarkov chainMonteCarlo data association,which can track an unknown number of targets. Distributed multitarget tracking and identity management manages identities of targets based on the identity-mass-flow framework. This framework prevents exponential growth in computation and storage of target-to-track association probabilities. Using identity and track fusion, distributed multitarget tracking and identity management maintains consistent identities and tracks among neighboring sensors. The performance and features of distributed multitarget tracking and identity management are extensively evaluated in simulation.