Abstract:
Target clustering is a quite important issue in situation assessment. To deal with the shortcomings of the existing target clustering algorithms, a multi-target hierarchical clustering method based on Louvain algorithm is proposed in this paper. Specifically, the problem of target clustering is formalized, then, the factors that should be considered when performing clustering operations at different levels are analyzed, finally, an appropriate distance metric used to measure the distance between targets is designed. The thought and the calculation process of the proposed algorithm are described in detail, and the approach to update the cluster parameters is explained at length. The effectiveness of the method is verified by simulation experiments.