Target Tracking Based on Amendatory Sage-Husa Adaptive Kalman Filtering

Abstract

-Aiming at the boundedness of target tracking inaccuracy, even the lost of tracking caused by the error accumulation and state mutation in the aspect of target tracking using Kalman filter. The paper proposes a novel algorithm which is based on the modified Sage-Husa adaptive Kalman filter. This algorithm adjusts the predicted value of Sage-Husa adaptive Kalman filter in time by setting judgment and amendment rules, which can inhibit accumulation of error on target tracking and improve the filter precision in steady state and strengthen the stability and adaptability of filter. The experimental results show that the effectiveness of the novel algorithm.

Optimized Sage–Husa filtering method for multitarget tracking with unknown detection profile

“…However, the noise variance cannot be accurately obtained owing to time-varying noise, which limits the application of the Sage–Husa filter to a certain extent (Du et al, 2018). To deal with this problem, Luo and Ren (2015) proposed a threshold criterion for the Sage–Husa filter. Liu et al (2019) presented an enhanced Sage–Husa filter by matching estimation covariance.…”