De-noising of laser self-mixing interference signal based on U-net network

Junwei Xu; Jinyuan Chen; Bin Liu

doi:10.1117/12.2687246

27 November 2023 De-noising of laser self-mixing interference signal based on U-net network

Junwei Xu, Jinyuan Chen, Bin Liu

Proceedings Volume 12761, Semiconductor Lasers and Applications XIII; 127610H (2023) https://doi.org/10.1117/12.2687246
Event: SPIE/COS Photonics Asia, 2023, Beijing, China

Abstract

Self-Mixing Interference (SMI) is promising high-precision measurement technology with advantage of compact structure, low implementation cost and high measurement resolution, which has been used in various applications in laboratory and engineering fields. However, measurement performance of an SMI sensor can be significantly affected by noises. In this paper we propose a solution based on the U-net, a popular deep learning scheme, to remove noises from SMI signals. U-net based deep learning is used to learn noise patterns and inherent levels from large sample data, and finally to denoise the SMI signals. Our proposed method can perform end-to-end neural network model training and directly process the original waveform. The results show that this method can effectively improve the signal-to-noise ratio of SMI signals. It is believed that this unified and precise method is able to lead to enhancement of performance of SMI laser sensors operating under noisy practical engineering conditions.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Junwei Xu, Jinyuan Chen, and Bin Liu "De-noising of laser self-mixing interference signal based on U-net network", Proc. SPIE 12761, Semiconductor Lasers and Applications XIII, 127610H (27 November 2023); https://doi.org/10.1117/12.2687246

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available