Scalar-weight interacting multiple model based on converted measurements Kalman filter

Abstract

In this study, we take advantage of the fusion criteria based- Scalar-weight Interacting Multiple Model (SIMM) algorithm and the Converted Measurements Kalman Filter (CMKF), which reduces the bias caused by coordinate transformations to propose a novel Interacting Multiple Model (IMM) tracking algorithm which uses multiple motion models for target tracking, The proposed algorithm has been tested on scenarios with highly maneuvering targets under heavy measurement noise. It is shown that the proposed algorithm has smaller estimation error compared to SIMM-KF and IMM-CMKF algorithms.