Abstract

The detection of adjacent vehicles in highway scenes has the problem of inaccurate clustering results. In order to solve this problem, this paper proposes a new clustering algorithm, namely Spindle-based Density Peak Fuzzy Clustering (SDPFC) algorithm. Its main feature is to use the density peak clustering algorithm to perform initial clustering to obtain the number of clusters and the cluster center of each cluster. The final clustering result is obtained by a fuzzy clustering algorithm based on the spindle update. The experimental data are the radar echo signal collected in the real highway scenes. Compared with the DBSCAN, FCM, and K-Means algorithms, the algorithm has higher clustering accuracy in certain scenes. The average clustering accuracy of SDPFC can reach more than 95%. It is also proved that the proposed algorithm has strong robustness in certain highway scenes.

Highlights

  • IntroductionRadar is an important part of the contemporary intelligent transportation system [1,2,3]

  • Radar is an important part of the contemporary intelligent transportation system [1,2,3].Multi-target tracking with radar is a hot issue in intelligent transportation research [4,5,6].By tracking passing vehicles, risky driving behavior can be predicted and an early warning signal can be issued [7,8]

  • This paper proposes a spindle-based density peak fuzzy clustering (SDPFC) algorithm

Read more

Summary

Introduction

Radar is an important part of the contemporary intelligent transportation system [1,2,3]. The purpose of this paper is to improve the cluster accuracy of adjacent vehicle sampling points in highway scenes. The algorithm uses a membership degree to determine the similarity of sample points It is a fuzzy clustering method based on the objective function [24,25,26]. For the inaccurate clustering results of adjacent vehicles in the highway scenes, this paper constructs a spindle-based density peak fuzzy clustering (SDPFC) system using traffic radar. This paper proposes a spindle-based density peak fuzzy clustering (SDPFC) algorithm. The ideal initial cluster center is calculated by finding the density peak In this way, the structure of the SDPFC algorithm is optimized.

Radar Signal Preprocessing
DBSCAN Clustering Algorithm
FCM Clustering Algorithm
Initial Clustering Algorithm Based on Density Peak
Fuzzy Clustering Algorithm Based on Spindle Update
Comparison of Experimental Results
Findings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call