model set design is an important area for multiple-mode estimation, and its main purpose is to design a suitable model set to improve the accuracy and stability of target tacking. In this article, a novel multiple mod...
详细信息
model set design is an important area for multiple-mode estimation, and its main purpose is to design a suitable model set to improve the accuracy and stability of target tacking. In this article, a novel multiplemodel estimation algorithm, namely, centroidfixed structure of interacting multiple-model estimation (CFIMM), is proposed to obtain the characteristic of the high precision and strong stability. First, the minimum distance method and the minimum model set method are, respectively, provided. Then, based on those two methods, the centroidmodel set design method is proposed with three different approaches to split the centroid. It proves that the centroidmodel set has minimal mathematical expectations with the actual models, when the unknown real model space is very large and even uncountable. Finally, the processing of the proposed CFIMM algorithm based on the centroidmodel set design method is discussed in detail. The proposed CFIMM holds not only the advantages of centroidmodel set but also the characteristic of the high precision and strong stability. The simulations of CFIMM highlight the correctness and effectiveness of the proposed methods.
暂无评论