FUZZY LABELING OF LOW-LEVEL DATA FROM AN ELECTROMAGNETIC SENSOR

DE602022019299T2Active Publication Date: 2025-08-13APTIV TECHNOLOGIES AG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
DE602022019299
Authority / Receiving Office
DE · DE
Patent Type
Patents
Current Assignee / Owner
Priority Date
2022-04-05
Filing Date
2022-09-26
Publication Date
2025-08-13
Estimated Expiration
2042-09-26

AI Technical Summary

Technical Problem

Automotive electromagnetic sensors lack sufficient high-quality labeled data, restricting the range of supervised learning tools available for electromagnetic sensor data processing, particularly due to challenges in segmenting and labeling radar data with geometric boundaries and spectrum smearing.

Method used

A fuzzy labeling system for radar data that segments and labels objects in the radar signal space, using low-level radar data to harness in-depth information from the energy distribution across range, range rate, azimuth, and elevation, enabling localization and segmentation of objects, and reducing false positives.

Benefits of technology

The fuzzy labeling system maximizes information extraction from radar signals, reduces false positives, and allows the model to adapt to different driving scenarios while maintaining performance, making it efficient for automotive applications with limited computing resources.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader
Need to check novelty before this filing date? Find Prior Art
No text content released.