Multiple Object Tracking: Case of Aircraft Detection and Tracking

Tracking has recently become one of the most interesting and active research fields. Tracking object consists in estimating the state of the object in function of time. This operation is based on largely developed filtering techniques. It is possible to classify tracking into Single Object Tracking and Multiple Object Tracking. This paper discusses the problem of multiple tracking. The aim is to encode a multiple object tracking algorithm to track aerial maneuvering aircraft by using the Interacting Multiple Model (IMM) combined with the assignment Global Nearest Neighbor (GNN) algorithm. The GNN represents the combinatorial optimization solution based on the comparison of different assignments.