A hybrid method for velocity field of fluid flow estimation based on optical flow

Abstract This research is mainly concerned with the characteristics of magnetohydrodynamics and Darcy–Forchheimer medium in nanofluid flow between two horizontal plates. A uniformly induced magnetic impact is involved at the direction normal to the lower plate. Darcy–Forchheimer medium is considered between the plates that allow the flow along horizontal axis with additional effects of porosity and friction. The features of Brownian diffusive motion and thermophoresis are disclosed. Governing problems are transformed into nonlinear ordinary problems using appropriate transformations. Numerical Runge–Kutta procedure is applied using MATLAB to solve the problems and acquire the data for velocity field, thermal distribution, and concentration distribution. Results have been plotted graphically. The outcomes indicate that higher viscosity results in decline in fluid flow. Thermal profile receives a decline for larger viscosity parameter; however, Brownian diffusion and thermophoresis appeared as enhancing factors for the said profile. Numerical data indicate that heat flux reduces for viscosity parameter. However, enhancement is observed in skin-friction for elevated values of porosity factor. Data of this paper are practically helpful in industrial and engineering applications of nanofluids.

Download Full-text

Optical flow and scene flow estimation: A survey

Pattern Recognition ◽

10.1016/j.patcog.2021.107861 ◽

2021 ◽

Vol 114 ◽

pp. 107861

Author(s):

Mingliang Zhai ◽

Xuezhi Xiang ◽

Ning Lv ◽

Xiangdong Kong

Keyword(s):

Optical Flow ◽

Flow Estimation ◽

Scene Flow

Download Full-text

An accurate optical flow estimation of PIV using fluid velocity decomposition

Experiments in Fluids ◽

10.1007/s00348-021-03176-w ◽

2021 ◽

Vol 62 (4) ◽

Author(s):

Jin Lu ◽

Hua Yang ◽

Qinghu Zhang ◽

Zhouping Yin

Keyword(s):

Optical Flow ◽

Fluid Velocity ◽

Flow Estimation ◽

Optical Flow Estimation ◽

Velocity Decomposition

Download Full-text

Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6699 ◽

2020 ◽

Vol 34 (07) ◽

pp. 10713-10720

Author(s):

Mingyu Ding ◽

Zhe Wang ◽

Bolei Zhou ◽

Jianping Shi ◽

Zhiwu Lu ◽

...

Keyword(s):

Optical Flow ◽

Video Segmentation ◽

Video Clip ◽

Semantic Segmentation ◽

Temporal Consistency ◽

Flow Estimation ◽

Optical Flow Estimation ◽

Optical Flows ◽

Benchmark Datasets ◽

Spatio Temporal

A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the frames. To exploit the spatio-temporal information in videos, many previous works use pre-computed optical flows, which encode the temporal consistency to improve the video segmentation. However, the video segmentation and optical flow estimation are still considered as two separate tasks. In this paper, we propose a novel framework for joint video semantic segmentation and optical flow estimation. Semantic segmentation brings semantic information to handle occlusion for more robust optical flow estimation, while the non-occluded optical flow provides accurate pixel-level temporal correspondences to guarantee the temporal consistency of the segmentation. Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference. Extensive experiments show that the proposed model makes the video semantic segmentation and optical flow estimation benefit from each other and outperforms existing methods under the same settings in both tasks.

Download Full-text