A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Deep-learning-based image preprocessing for particle image velocimetry
https://orcid.org/0000-0002-4121-0261
Abstract Particle image velocimetry (PIV) is an important measurement technique for estimating global fluid motion by capturing particle motion from a pair of images. Hence, obtaining high-quality particle images is critical for a PIV estimation. The purpose of this study is to propose a deep-learning-based technique for PIV image preprocessing. Specifically, we first designed a deep convolutional network called Bilateral-CNN for a pair image preprocessing task, which embeds residual learning and batch normalization. Bilateral-CNN fully considers the feature connections between image pairs. Second, to train our model, we generate a synthetic dataset that includes Gaussian noise and various light intensities. Considering a real fluid scene, different background information such as rising bubbles is superposed into the images, which makes the particle images more challenging. Finally, we conducted experiments on synthetic and experimental particle images. Extensive results indicate that our method can effectively overcome the particle image interference noise under different situations. In addition, the processed particle images are calculated using cross-correlation WIDIM algorithm, and a high-precision velocity field is obtained by fast inference speed.
Highlights We presents a neural network model, Bilateral-CNN, for PIV images pre-processing. A set of synthetic particle image including complex disturbances are made. Particle images processed by Bilateral-CNN obtain more prominent correlation peaks than traditional methods. Bilateral-CNN effectively reduces the number of velocity vector errors calculated.
Deep-learning-based image preprocessing for particle image velocimetry
https://orcid.org/0000-0002-4121-0261
Abstract Particle image velocimetry (PIV) is an important measurement technique for estimating global fluid motion by capturing particle motion from a pair of images. Hence, obtaining high-quality particle images is critical for a PIV estimation. The purpose of this study is to propose a deep-learning-based technique for PIV image preprocessing. Specifically, we first designed a deep convolutional network called Bilateral-CNN for a pair image preprocessing task, which embeds residual learning and batch normalization. Bilateral-CNN fully considers the feature connections between image pairs. Second, to train our model, we generate a synthetic dataset that includes Gaussian noise and various light intensities. Considering a real fluid scene, different background information such as rising bubbles is superposed into the images, which makes the particle images more challenging. Finally, we conducted experiments on synthetic and experimental particle images. Extensive results indicate that our method can effectively overcome the particle image interference noise under different situations. In addition, the processed particle images are calculated using cross-correlation WIDIM algorithm, and a high-precision velocity field is obtained by fast inference speed.
Highlights We presents a neural network model, Bilateral-CNN, for PIV images pre-processing. A set of synthetic particle image including complex disturbances are made. Particle images processed by Bilateral-CNN obtain more prominent correlation peaks than traditional methods. Bilateral-CNN effectively reduces the number of velocity vector errors calculated.
Deep-learning-based image preprocessing for particle image velocimetry
https://orcid.org/0000-0002-4121-0261
Abstract Particle image velocimetry (PIV) is an important measurement technique for estimating global fluid motion by capturing particle motion from a pair of images. Hence, obtaining high-quality particle images is critical for a PIV estimation. The purpose of this study is to propose a deep-learning-based technique for PIV image preprocessing. Specifically, we first designed a deep convolutional network called Bilateral-CNN for a pair image preprocessing task, which embeds residual learning and batch normalization. Bilateral-CNN fully considers the feature connections between image pairs. Second, to train our model, we generate a synthetic dataset that includes Gaussian noise and various light intensities. Considering a real fluid scene, different background information such as rising bubbles is superposed into the images, which makes the particle images more challenging. Finally, we conducted experiments on synthetic and experimental particle images. Extensive results indicate that our method can effectively overcome the particle image interference noise under different situations. In addition, the processed particle images are calculated using cross-correlation WIDIM algorithm, and a high-precision velocity field is obtained by fast inference speed.
Highlights We presents a neural network model, Bilateral-CNN, for PIV images pre-processing. A set of synthetic particle image including complex disturbances are made. Particle images processed by Bilateral-CNN obtain more prominent correlation peaks than traditional methods. Bilateral-CNN effectively reduces the number of velocity vector errors calculated.
Deep-learning-based image preprocessing for particle image velocimetry
Fan, Yiwei (author) / Guo, Chunyu (author) / Han, Yang (author) / Qiao, Weizheng (author) / Xu, Peng (author) / Kuai, Yunfei (author)
Applied Ocean Research ; 130
2022-11-01
Article (Journal)
Electronic Resource
English
Particle image velocimetry in thermal spraying
| British Library Online Contents | 2004
Particle-Image Velocimetry for Ice-Field Velocities
| British Library Conference Proceedings | 1997
MULTI-CAMERA LARGE-SCALE PARTICLE IMAGE VELOCIMETRY
| TIBKAT | 2020
Track deflection measurement using particle image velocimetry
British Library Online Contents | 2009
Particle image velocimetry validation for quantifying bedload movement
| Taylor & Francis Verlag | 2019