Distance Measurement of Cluster Analysis for Point Cloud Data in Unmanned System

In unmanned systems, the point cloud segmentation is one of the most important tasks in data processing. This paper proposes a distance measurement of clustering analysis for the point cloud data of the unmanned system. The proposed method can be seemed as two steps. Firstly, the mathematical formula and norm function are used for the UCI standard sets, such as ECOLI and IRIS. After evaluating the parameters, the suitable formula is adopted for subsequent experimental analysis. Then experiments are carried out by the F measurement, the error rate and the Minkowski score, which are three evaluation indicators estimate the impact of the distance measurement on the cluster analysis. Finally, the experiments conclude that the Minkowski distance measurement method can be used for the cluster analysis of unmanned systems.