A Cluster-Based Weighted Feature Similarity Moving Target Tracking Algorithm for Automotive FMCW Radar

TL;DR

This paper introduces a novel cluster-based weighted feature similarity algorithm for moving target tracking in automotive FMCW radar, improving matching accuracy under noisy conditions and enabling effective trajectory correction in autonomous driving.

Contribution

It proposes a new weighted feature similarity algorithm and a motion parameter-based trajectory correction method tailored for autonomous driving radar scenarios.

Findings

High recognition accuracy demonstrated in experiments

Low positional error achieved in target tracking

Effective in environments with strong noise and multiple targets

Abstract

We studied a target tracking algorithm based on millimeter-wave (MMW) radar in an autonomous driving environment. Aiming at the cluster matching in the target tracking stage, a new weighted feature similarity algorithm is proposed, which increases the matching rate of the same target in adjacent frames under strong environmental noise and multiple interference targets. For autonomous driving scenarios, we constructed a method that uses its motion parameters to extract and correct the trajectory of a moving target, which solves the problem of moving target detection and trajectory correction during vehicle movement. Finally, the feasibility of the proposed method was verified by a series of experiments in autonomous driving environments. The results verify the high recognition accuracy and low positional error of the method.