A Scalable Multitarget Tracking System for Cooperative Unmanned Aerial Vehicles

Abstract

In this paper, we present a decentralized multitarget tracking system for cooperative unmanned aerial vehicles (UAVs) with limited sensing capabilities. The proposed system distributively incorporates a clustering algorithm, an optimal sensor manager, and an optimal path planner to track multiple mobile targets. A set of extended Kalman filters is used by each UAV to estimate the locations of mobile targets. The UAVs are equipped with gimbaled cameras with a limited field of view and sensing range. To make the system scalable, the density-based spatial clustering of applications with noise algorithm is used to group targets, sensor managers determine optimal gimbal poses and path planners collectively coordinate UAVs' movements. The effective performance of the proposed system is shown through simulation results.