Abstract
Streamlining is one of the most frequently utilized visualization methods to analyze the flow structure of computational fluid dynamics (CFD) data. However, it is challenging to find a set of streamlines showing the most prominent flow across the entire flow field due to the heavy computation time required to generate bundles of streamlines. In this paper, we propose an efficient streamline generation method that removes several seed candidates that are predicted as less important using a 3D U-net based regression model. We employ 3D line integral convolution (LIC) volumes that depict the entire flow field for training data of the proposed learning model and evaluate our method using a real-world CFD data set. We find using our model that we can obtain quality of visualization results comparable to that of the ground truth even when more than 90% of the seed candidates are truncated while operating 6.6~17.1 times faster than the competing method.
Highlights
Streamline is a curved line which is instantaneously tangential to the velocity vector in the flow field
Many semantic segmentation networks have adopted an encoder-decoder style of architecture based on a fully convolutional network (FCN) [5] for pixel-level classification to segment input images
A receptive field that is too large may lead to lower accuracy due to the excessive influence of distant voxels, which may be unrelated
Summary
Streamline is a curved line which is instantaneously tangential to the velocity vector in the flow field. The associate editor coordinating the review of this manuscript and approving it for publication was Lei Wei. This paper introduces a 3D U-net-based deep regression model that predicts the importance of streamlines generated from densely located seed points in a 3D velocity field. Unlike most other FCN based models, our network uses regression to predict the floating-point values of importance scores across all voxels, in other words, it undertakes a voxel-wise regression This step is designed to predict the importance of the streamlines generated from resampled seed points in the input flow field.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have