LightPIVNet: An Effective Convolutional Neural Network for Particle Image Velocimetry

Yu, Changdong; Bi, Xiaojun; Yi, Fan; Han, Yang; Kuai, Yun-fei

doi:10.1109/tim.2021.3082313

Cited by 28 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning technology, as the most important branch of machine learning, has achieved great success in various fields because of its powerful feature representation ability [ 26 , 27 , 28 ]. Compared with machine learning, deep learning models can handle mass and complicated data, which is required for processing complicated fingerprint data.…”

Section: Related Workmentioning

confidence: 99%

SASMOTE: A Self-Attention Oversampling Method for Imbalanced CSI Fingerprints in Indoor Positioning Systems

Liu

Cheng

2022

Sensors

Self Cite

View full text Add to dashboard Cite

WiFi localization based on channel state information (CSI) fingerprints has become the mainstream method for indoor positioning due to the widespread deployment of WiFi networks, in which fingerprint database building is critical. However, issues, such as insufficient samples or missing data in the collection fingerprint database, result in unbalanced training data for the localization system during the construction of the CSI fingerprint database. To address the above issue, we propose a deep learning-based oversampling method, called Self-Attention Synthetic Minority Oversampling Technique (SASMOTE), for complementing the fingerprint database to improve localization accuracy. Specifically, a novel self-attention encoder-decoder is firstly designed to compress the original data dimensionality and extract rich features. The synthetic minority oversampling technique (SMOTE) is adopted to oversample minority class data to achieve data balance. In addition, we also construct the corresponding CSI fingerprinting dataset to train the model. Finally, extensive experiments are performed on different data to verify the performance of the proposed method. The results show that our SASMOTE method can effectively solve the data imbalance problem. Meanwhile, the improved location model, 1D-MobileNet, is tested on the balanced fingerprint database to further verify the excellent performance of our proposed methods.

show abstract

Section: Related Workmentioning

confidence: 99%

SASMOTE: A Self-Attention Oversampling Method for Imbalanced CSI Fingerprints in Indoor Positioning Systems

Liu

Cheng

2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Noteworthy characteristics of PIV-LiteFlowNet-en include specialized flow regularization techniques for smoothing velocity fields, managing motions of varying scales, and employing feature warping to minimize the discrepancy between pyramid levels in the encoder [13]. Based on the recurrent all-pairs field transforms (RAFTs) architecture [14], Yu et al proposed LightPIVNet, which had 47% fewer parameters and 14% reduced calculation time compared to PIV-LiteFlowNet-en [15]. Subsequently, Lagemann et al adapted RAFT to RAFT-PIV [16], thereby achieving state-of-the-art accuracy and performance in the field of PIV using optical flow estimation.…”

Section: Introductionmentioning

confidence: 99%

Experimental dataset investigation of deep recurrent optical flow learning for particle image velocimetry: flow past a circular cylinder

Anjaneya Reddy,

Wahl,

Sjödahl

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Current optical flow-based neural networks for Particle Image Velocimetry (PIV) are largely trained on synthetic datasets emulating real-world scenarios. While synthetic datasets provide greater control and variation than what can be achieved using experimental datasets for supervised learning, it requires a deeper understanding of how or what factors dictate the learning behaviors of deep neural networks for PIV. In this study, we investigate the performance of the Recurrent All-Pairs Field Transforms (RAFT-PIV) network, the current state-of-the-art deep learning architecture for PIV, by testing it on unseen experimentally generated datasets. The results from RAFT-PIV are compared with a conventional cross-correlation-based method, Adaptive PIV. The experimental PIV datasets were generated for a typical scenario of flow past a circular cylinder in a rectangular channel. These test datasets encompassed variations in particle diameters, particle seeding densities, and flow speeds, all falling within the parameter range used for training RAFT-PIV. We also explore how different image pre-processing techniques can impact and potentially enhance the performance of RAFT-PIV on real-world datasets. Thorough testing with real-world experimental PIV datasets reveals the resilience of the optical flow-based method’s variations to PIV hyperparameters, in contrast to the conventional PIV technique. The ensemble-averaged Root Mean Squared Errors (RMSE) between the RAFT-PIV and Adaptive PIV estimations generally range between 0.5 to 2 [px] and show a slight reduction as particle densities increase or Reynolds numbers decrease. Furthermore, findings indicate that employing image pre-processing techniques to enhance input particle image quality doesn't improve RAFT-PIV predictions; instead, it incurs higher computational costs and impacts estimations of small-scale structures.

show abstract

“…Convolutional Neural Network (CNN) architectures have been proposed for optical motion analysis [6][7][8], and more recently for PIV [9][10][11][12][13][14][15][16][17][18], as an alternative to conventional two-dimensional (2D) image cross-correlation (such as state-of-the-art Window Deformation Iterative Multigrid, WIDIM [2,19,20]). CNNs require very large training sets due to the complexity of the networkparameter space that may include up to millions of free trainable variables.…”

Section: Introductionmentioning

confidence: 99%

A lightweight convolutional neural network to reconstruct deformation in BOS recordings

Mucignat

Manickathan

Shah

et al. 2023

Preprint

View full text Add to dashboard Cite

We introduce a Convolutional Neural Network (CNN) that is specificallydesigned and trained to post-process recordings obtained by BackgroundOriented Schlieren (BOS), a popular technique to visualize compressibleand convective flows. To reconstruct BOS image deformation, we deviseda lightweight network (LIMA) that has comparatively fewer parameters totrain than the CNNs that have been previously proposed for optical flow.To train LIMA, we introduce a novel strategy based on the generation of synthetic images from random-irrotational deformation fields, which areintended to mimic those provided by real BOS recordings. This allows us to generate a large number of training examples at minimal compu-tational cost. To assess the accuracy of the reconstructed displacements,we consider test cases consisting of synthetic images with sinusoidal dis-placement as well as images obtained in the experimental studies of a hotplume in air and a flow past and inside a heated hollow hemisphere. By comparing the reconstructed deformation fields using the LIMA or conven-tional post-processing techniques used in Direct Image Correlation (dic)or conventional image cross-correlation, we show that LIMA is more accu-rate and robust in the synthetic test case. When applied to experimentalBOS recordings, all methods provide similar and consistent deformation fields. As LIMA is capable of achieving a comparable or better accuracyat a fraction of the computational costs, it represents a valuable alternative to conventional post-processing techniques for BOS experiments.

show abstract

LightPIVNet: An Effective Convolutional Neural Network for Particle Image Velocimetry

Cited by 28 publications

References 36 publications

SASMOTE: A Self-Attention Oversampling Method for Imbalanced CSI Fingerprints in Indoor Positioning Systems

SASMOTE: A Self-Attention Oversampling Method for Imbalanced CSI Fingerprints in Indoor Positioning Systems

Experimental dataset investigation of deep recurrent optical flow learning for particle image velocimetry: flow past a circular cylinder

A lightweight convolutional neural network to reconstruct deformation in BOS recordings

Contact Info

Product

Resources

About