Target tracking method, device, equipment and medium

By employing the nearest neighbor algorithm and filters to update track estimates in millimeter-wave radar, and combining this with a road model to determine track status, the problem of track fragmentation in target tracking is solved, achieving higher tracking accuracy.

CN115755019BActive Publication Date: 2026-07-07HUIZHOU DESAY SV AUTOMOTIVE
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUIZHOU DESAY SV AUTOMOTIVE
Filing Date
2022-07-27
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

In existing target tracking technologies, when the target's echo is blocked by obstacles or its speed is reduced to below the radar speed measurement threshold, the track breaks down, making it impossible to accurately track the target.

Method used

By acquiring the measurement point dataset and prediction result set of millimeter-wave radar, the nearest neighbor algorithm is used for correlation, combined with Bayesian filtering and CKF filter, the track estimation value is updated, the track status is determined by road model, and the track dataset is merged to solve the track fragmentation problem.

Benefits of technology

It improves the accuracy of target tracking trajectory results, ensuring accurate target tracking even when obstructed by obstacles or at low speeds, and reduces trajectory breakage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115755019B_ABST
    Figure CN115755019B_ABST
Patent Text Reader

Abstract

The application discloses a target tracking method, device, equipment and medium. The method comprises the following steps: acquiring a measurement point data set of a current frame collected by a millimeter wave radar, obtaining an association result according to a predetermined prediction result set and the measurement point data set; updating a track estimation value of the current frame according to the association result; and determining a target track set corresponding to a tracking target according to the track estimation value. By inputting the measurement point data set of the current frame collected by the millimeter wave radar and a prediction result of a previous frame into a set association and updating algorithm, the target track set is obtained, the determination of the tracking target track is realized, the problem of track breakage in the tracking process is solved, and the accuracy of the track result is improved.
Need to check novelty before this filing date? Find Prior Art