Density Estimation from Schlieren Images through Machine Learning

Ubald, Bryn N.; Seshadri, Pranay; Duncan, Andrew

doi:10.48550/arxiv.2201.05233

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model successfully identified hidden flow structures that were undetectable by traditional methods. Additionally, Ubald et al [25] presented a Gaussian process model-based approach for extracting quantitative flow information from schlieren images. Various deep learning techniques were also explored for shock wave detection in a number of other papers.…”

Section: Introductionmentioning

confidence: 99%

Анализ Экспериментальных Теневых Изображений Течений Методами Компьютерного Зрения

Doroshchenko

2023

NMP

View full text Add to dashboard Cite

In this study, two examples of physical experiment automation using computer vision and deep learning techniques are considered. The first of them involves the use of classical computer vision techniques to detect and track the oblique shock wave on the experimental shadowgraph images. This was achieved using Canny edge detection and Hough transform, which allowed to obtain the line equation corresponding to the oblique shock wave. By automatically calculating the angle of this wave for each frame in the video, the process of extracting quantitative information from flow visualizations was significantly accelerated. In the second example, a convolutional neural network was trained to identify four classes of objects on the shadowgraph images, namely vertical shock waves, bow shocks, plumes, and opaque particles in the flow. The custom object detection model is based on the up-todate YOLOv8 architecture. To realize this task, a dataset of 1493 labeled shadowgraph images was collected. The model showed excellent performance during the learning process, with model precision and mAP50 scores exceeding 0.9. It was successfully applied to detect objects on the shadowgraph images, demonstrating the potential of deep learning techniques for automating the processing of flow visualizations. Overall, this study highlights the significant benefits of combining classical computer vision algorithms with deep learning techniques in the automation of physical experiments. However, classical algorithms demand the writing additional code to extract the required information. The deep neural networks can perform this task automatically, provided that a well-annotated dataset is available. This approach offers a promising avenue for accelerating the analysis of flow visualizations and the extraction of quantitative information in physical experiments. computer vision, digital image processing, object detection, convolutional neural networks, flow visualization, shock wave, bow shock В данном исследовании рассматриваются два примера автоматизации физических экспериментов с использованием методов компьютерного зрения и глубокого обучения. В первом из них были применены классические алгоритмы компьютерного зрения для обнаружения и отслеживания косого скачка уплотнения на экспериментальных теневых изображениях: метод выделения границ Кэнни и преобразование Хафа. Получив уравнение прямой, соответствующей косому скачку уплотнения, угол ее наклона автоматически рассчитывался для каждого кадра видео. Во втором примере была обучена сверточная нейронная сеть для определения четырех классов объектов на теневых изображениях: вертикальных ударных волн, головных ударных волн, термиков и непрозрачных частиц в потоке. Модель основана на современной архитектуре YOLOv8. Для реализации этой задачи был создан набор данных из 1493 размеченных теневых изображений. Модель показала хорошие метрики в процессе обучения: точность модели и оценка mAP50 превысили 0,9. Она была успешно применена для обнаружения объектов на теневых изображениях. Было продемонстрировано, что применение классических алгоритмов компьютерного зрения и глубокого обучения может значительно ускорить обработку визуализаций потоков и извлечение количественной информации. Однако классические алгоритмы обычно не могут использоваться напрямую и требуют от исследователя написания дополнительного кода для извлечения необходимой информации. Глубокие нейронные сети могут выполнить эту задачу автоматически, и единственное, что требуется, это разметка и сбор большего набора данных.

show abstract

Section: Introductionmentioning

confidence: 99%

Анализ Экспериментальных Теневых Изображений Течений Методами Компьютерного Зрения

Doroshchenko

2023

NMP

View full text Add to dashboard Cite

show abstract

“…It was found that the neural network can obtain finer and hidden flow structures, which cannot be resolved with the cross-correlation method. Ubald et al [16] proposed a method based on the Gaussian process model for extracting quantitative information from schlieren images. A pair of schlieren images with the knife-edge at horizontal and vertical orientations was used to extract density values from the images.…”

Section: Introductionmentioning

confidence: 99%

High-speed Flow Structures Detection and Tracking in Multiple Shadow Images with Matching to CFD using Convolutional Neural Networks

Doroshchenko¹,

Znamenskaya²,

Sysoev³

et al. 2022

View full text Add to dashboard Cite

Shadowgraph imaging has been widely used to study flow fields in experimental fluid dynamics. Nowadays high-speed cameras allow to obtain millions of frames per second. Thus, it is not possible to analyze and process such large data sets manually and automatic image processing software is required. In the present study a software for automatic flow structures detection and tracking was developed based on the convolutional neural network (the network architecture is based on the YOLOv2 algorithm). Auto ML techniques were used to automatically tune model and hyperparameters and speed-up model development and training process. The neural network was trained to detect shock waves, thermal plumes, and solid particles in the flow with high precision. We successfully tested out software on high-speed shadowgraph recordings of gas flow in shock tube with shock wave Mach number M = 2-4.5. Also, we performed CFD to simulate the same flow. In recent decades, the amount of data in numerical simulations has grown significantly due to the growth in performance of computers. Thus, machine learning is also required to process large arrays of CFD results. We developed another ML tool for experimental and simulated by CFD shadowgraph images matching. Our algorithm is based on the VGG16 deep neural network for feature vector extraction and knearest neighbors algorithm for finding the most similar images based on the cosine similarity. We successfully applied our algorithm to automatically find the corresponding experimental shadowgraph image for each CFD image of the flow in shock tube with a rectangular obstacle in the flow channel.

show abstract

Gas Flow Structures Detection on Shadowgraph Images and Their Matching to CFD Using Convolutional Neural Networks

Doroshchenko

Znamenskaya

Lutsky³

2022

Proceedings of the 32nd International Conference on Computer Graphics and Vision

View full text Add to dashboard Cite

Shadowgraph imaging has been widely used to study flow fields in experimental fluid dynamics. Nowadays high-speed cameras allow to obtain millions of frames per second. Thus, it is not possible to analyze and process such large data sets manually and automatic image processing software is required. In the present study a software for automatic flow structures detection and tracking was developed based on the convolutional neural network (the network architecture is based on the YOLOv2 algorithm). Auto ML techniques were used to automatically tune model and hyperparameters and speed-up model development and training process. The neural network was trained to detect shock waves, thermal plumes, and solid particles in the flow with high precision. We successfully tested out software on high-speed shadowgraph recordings of gas flow in shock tube with shock wave Mach number M = 2-4.5. Also, we performed CFD to simulate the same flow. In recent decades, the amount of data in numerical simulations has grown significantly due to the growth in performance of computers. Thus, machine learning is also required to process large arrays of CFD results. We developed another ML tool for experimental and simulated by CFD shadowgraph images matching. Our algorithm is based on the VGG16 deep neural network for feature vector extraction and k-nearest neighbors algorithm for finding the most similar images based on the cosine similarity. We successfully applied our algorithm to automatically find the corresponding experimental shadowgraph image for each CFD image of the flow in shock tube with a rectangular obstacle in the flow channel.

show abstract

Density Estimation from Schlieren Images through Machine Learning

Cited by 3 publications

References 15 publications

Анализ Экспериментальных Теневых Изображений Течений Методами Компьютерного Зрения

Анализ Экспериментальных Теневых Изображений Течений Методами Компьютерного Зрения

High-speed Flow Structures Detection and Tracking in Multiple Shadow Images with Matching to CFD using Convolutional Neural Networks

Gas Flow Structures Detection on Shadowgraph Images and Their Matching to CFD Using Convolutional Neural Networks

Contact Info

Product

Resources

About