SIMM Method Based on Acceleration Extraction for Nonlinear Maneuvering Target Tracking

Abstract

-This paper presents the smart interacting multiple model (SIMM) using the concept of predicted point and maximum noise level. Maximum noise level means the largest value of the mere noises. We utilize the positional difference between measured point and predicted point as acceleration. Comparing this acceleration with the maximum noise level, we extract the acceleration to recognize the characteristics of the target. To estimate the acceleration, we propose an optional algorithm utilizing the proposed method and the Kalman filter (KF) selectively. Also, for increasing the effect of estimation, the weight given at each sub-filter of the interacting multiple model (IMM) structure is varying according to the rate of noise scale. All the procedures of the proposed algorithm can be implemented by an on-line system. Finally, an example is provided to show the effectiveness of the proposed algorithm.

Fuzzy c‐means clustering‐based smart tracking model for three‐dimensional manoeuvring target including unknown acceleration input

“…Step 1 (Initialisation): Substituting the predicted point 1 d (k|k − 1) into the measurement z d (k|k) yields the estimated positional errorê d (k|k − 1) from the aforementioned (1), (2), (3), (13) and (14). The set E(k|k − 1) is used as the input data of the segmentalised FCM as shown in the Fig.…”

“…Tracking problems including target dynamics, manoeuvring target tracking and measurement origin uncertainty are components not only in military applications, but also closely linked to other areas of human life [3–6]. In order to solve these computational problems, a variety of techniques have been studied and developed in the field of state estimation over a period of decades [7–13].…”

Smart tracking algorithm for multi‐static sonar based on expectation maximisation

“…Third, the measurement should be processed adaptively when unknown external inputs are included in the manoeuvres of the target [18–20]. In particular, the acceleration inputs should be separated from the noise term and should be offset appropriately to improve the tracking performance [21–23]. Fourth, the dispersion of the measurement residuals should be analysed to enhance the tracking performance.…”

Fuzzy c ‐means‐based intelligent tracking algorithm for an underwater manoeuvring target

“…A variety of techniques have been studied and developed in the field of state estimation over many decades to resolve this ambiguity in the error component related to the complex manoeuvring [4–10]. The following three methods are used from a modelling perspective: firstly, the discrete‐time model is commonly used since the evolution of the digital computer.…”