CAN: Classification-Based Autoencoder Network for Enhanced Out-of-Distribution Detection in Radar-Based Hand Gesture Recognition

Janjua MG, Kaiser K, Stadelmayer T, Schoenfeldt S, Issakov V (2024)

Publication Type: Conference contribution

Publication year: 2024

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 16-20

Conference Proceedings Title: 2024 9th International Conference on Frontiers of Signal Processing, ICFSP 2024

Event location: Paris FR

ISBN: 9798350353235

DOI: 10.1109/ICFSP62546.2024.10785515

Abstract

Out-of-distribution (OOD) detection is essential for the robustness of radar-based gesture recognition systems. This paper proposes Classification-Based Autoencoder Network (CAN), as a novel OOD detection approach for radar-based hand gesture recognition. CAN uses an autoencoder to reconstruct radar gesture data, integrated with a classifier to learn a discriminative latent space, resulting in improved OOD detection performance. The evaluation of CAN is conducted on a dataset consisting of nine in-distribution gesture classes and a challenging OOD dataset containing six gestures that closely resemble the in-distribution gestures. The results indicate that CAN substantially improves the detection of challenging OOD radar samples compared to current state-of-the-art (SOTA) methods. It reduces the false positive rate (FPR) to 21%, which is significantly lower than the 58% FPR of the existing baseline. Additionally, it achieves an Area under the receiver operating characteristic curve (AUROC) of 95%, surpassing the 78% AUROC of the baseline method.

Authors with CRIS profile

Kevin Kaiser Lehrstuhl für Technische Elektronik (LTE) Thomas Stadelmayer Lehrstuhl für Technische Elektronik (LTE)

Involved external institutions

Technische Universität Braunschweig DE Germany (DE) Infineon Technologies AG DE Germany (DE)

How to cite

APA:

Janjua, M.G., Kaiser, K., Stadelmayer, T., Schoenfeldt, S., & Issakov, V. (2024). CAN: Classification-Based Autoencoder Network for Enhanced Out-of-Distribution Detection in Radar-Based Hand Gesture Recognition. In 2024 9th International Conference on Frontiers of Signal Processing, ICFSP 2024 (pp. 16-20). Paris, FR: Institute of Electrical and Electronics Engineers Inc..

MLA:

Janjua, Muhammad Ghufran, et al. "CAN: Classification-Based Autoencoder Network for Enhanced Out-of-Distribution Detection in Radar-Based Hand Gesture Recognition." Proceedings of the 9th International Conference on Frontiers of Signal Processing, ICFSP 2024, Paris Institute of Electrical and Electronics Engineers Inc., 2024. 16-20.

BibTeX: Download