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
Jasmin Gabsteiger
Lehrstuhl für Technische Elektronik
Timo Maiwald
Lehrstuhl für Technische Elektronik
Robert Weigel
Lehrstuhl für Technische Elektronik
Additional Organisation(s)
Related research project(s)
Involved external institutions
Germany (DE)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