Paper
12 October 2022 Temperature imaging network based on swin transformer for TDLAS tomography
Author Affiliations +
Proceedings Volume 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022); 123422N (2022) https://doi.org/10.1117/12.2643397
Event: Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 2022, Wuhan, China
Abstract
Most of existing data-driven temperature imaging schemes for Tunable Diode Laser Absorption Spectroscopy (TDLAS) tomography are based on Convolutional Neural Network (CNN). However, some studies on CNN show that its actual perceptual field is much smaller than the theoretical one, which makes it not conducive for CNN to capture features from contextual information at long distance. In this work, a temperature imaging network based on Swin Transformer is established. To introduce cross-window connections while maintaining the efficient computation of local non-overlapped windows, Multi-headed Self-Attention (MSA) is computed alternatively in regularly partitioned windows and shifted windows. Simulation results show that the proposed network can reconstruct temperature images of higher quality than schemes based on CNN and Extreme Learning Machine (ELM) respectively.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jingjing Si, Aiting Wang, and Yinbo Cheng "Temperature imaging network based on swin transformer for TDLAS tomography", Proc. SPIE 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 123422N (12 October 2022); https://doi.org/10.1117/12.2643397
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Transformers

Reconstruction algorithms

Tomography

Back to Top