Automated Radar Data Labeling through Computer Vision

Gabsteiger J, Maiwald T, Wünsche S, Weigel R, Lurz F (2023)


Publication Status: Accepted

Publication Type: Conference contribution

Future Publication Type: Conference contribution

Publication year: 2023

Event location: Melbourne, FL 32903

DOI: 10.1109/WAMICON57636.2023.10124886

Abstract

This paper presents the combination of an existing computer vision model with a highly integrated mmwave radar system for automated radar data labeling. A pre trained model for person presence detection is used in combination with a camera sensor to determine, whether a person is present or not. The binary prediction is used to label simultaneously measured radar data of the same scenery. The paper addresses the challenges of varying illumination conditions, camera and radar sensor aperture angles and data quality which are dominant influences at the labeling process. The system significantly decreases human effort by automating the labeling process. It is used to generate 10,000 data points, label them and train a neural network with 95.7% accuracy. Finally, a proof-of-concept, training, and evaluation of radarbased activity detection with automatically labeled data is presented. The proposed method can contribute in person presence detection under challenging light conditions.

Authors with CRIS profile

Additional Organisation(s)

Related research project(s)

Involved external institutions

How to cite

APA:

Gabsteiger, J., Maiwald, T., Wünsche, S., Weigel, R., & Lurz, F. (2023). Automated Radar Data Labeling through Computer Vision. In Proceedings of the Wamicon. Melbourne, FL 32903.

MLA:

Gabsteiger, Jasmin, et al. "Automated Radar Data Labeling through Computer Vision." Proceedings of the Wamicon, Melbourne, FL 32903 2023.

BibTeX: Download