Joint tracking and classification with constraints and reassignment by radar and ESM

We consider the problem of joint tracking and classification using the information from radar and electronic support measure. For each target class, a separate filter is operated in parallel, and each class-dependent filter is implemented by interacting multiple model regularized particle filter. The speed likelihood for each class is defined using a priori information about speed constraint and combined with the likelihoods from two sensors to improve tracking and classification. Moreover, the output of classifier is also used for particle reassignment of different classes, which might lead to better performance. Simulations show that our proposed method can provide reliable tracking and correct classification. It uses information from radar and ESM to avoid the kinematic-only classification.For each class, a separate filter is operated in parallel and implemented by IMMRPF.Speed likelihood for each class is calculated and combined with likelihoods from two sensors.Output of classifier is also used for particle reassignment of different classes.