Bubble Trajectory Tracking Based on ORB Algorithm
DOI:
https://doi.org/10.5566/ias.2794Keywords:
edge detection, feature matching, gas-liquid two-phase flow, trackingAbstract
The system of gas-liquid two-phase bubbly flows is widely found in many industrial fields, such as nuclear energy, chemical, petroleum, and refrigeration. Bubbly two-phase flows measuring including detection and tracking affects the specific engineering problem solving to a great extent. The particle tracking velocity (PTV) algorithm is generally used for the tracking of the particles in the flow field. However, it does not take the shape change of particles into account in the process of flow. In this paper, a kind of bubble feature matching method based on ORB algorithm is proposed, and the edge detection method of findContours in OpenCV is used to extract the bubble contour in the image. The proposed algorithm implements the trajectory tracking of the bubbles with shape change when moving up in liquid. The feasibility of bubble trajectory tracking is shown by displaying of different bubble tracks in the plan, 3D plots and contour changing plots.
References
Augustyniak J, Perkowski D, Mosdorf R (2020).
Measurement of multifractal character of bubble paths using image analysis. INT COMMUN HEAT MASS 117: 104701.
Bay H, Tuytelaars T, Gool L V(2006). SURF:
Speeded up robust features. LECT NOTES COMPUT SC 51: 404-17.
Gandhi M, Kamdar J, Shah M (2020).
Preprocessing of non-symmetrical images for edge detection. Augment Hum Res 5: 1-10.
Harris C, Stephens M(1988). A combined corner
and edge detector. AVC 15: 10-5244.
Igor P, Mikhail P, Konstantin S (2020). Bubble
patterns recognition using neural networks: Application to the analysis of a two-phase bubbly jet. INT J MULTIPHAS FLOW 126: 103194.
Kolaas J, Drazen D, Jensen A (2015). Lagrangian
measurements of two-phase pipe flow using combined PIV/PTV. J DISPER SCI TECHNOL 36: 1473-82.
Lowe DG(1999). Object recognition from local
scale-invariant features. In: Proceedings of the seventh IEEE international conference on computer vision, ICCV 1999.
Lowe DG (2004). Distinctive image features
from scale-invariant keypoints. INT J COMPUT VISION 60: 91-110.
Liu C, Tao L(2007). Two-dimensional digital
particle tracking velocimetry algorithm based on the image of particle trace. J COASTAL RES: 415-19.
Li Y, Liu B (2022). Improved edge detection algorithm for canny operator. 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), p. 1-5.
Mikolajczyk K, Schmid C(2004) . Scale &
Affine Invariant Interest Point Detectors. INT J COMPUT VISION 2004:63-86.
Qin Y, Xu H, Chen H (2014). Image feature
points matching via improved ORB. 2014 IEEE International Conference on Progress in Informatics and Computing (PIC). IEEE, 2014: 204-8.
Rublee E, Rabaud V, Konolige K, et al (2011).
ORB: An efficient alternative to SIFT algorithm or SURF algorithm. 2011 International conference on computer vision, ICCV 2011.
Suzuki S (1985). Topological structural analysis
of digitized binary images by border following. COMPUT VISION GRAPH 30: 32-46.
Sokoray-Varga B, Józsa J(2008).
Particle tracking velocimetry (PTV) and its application to analyse free surface flows in laboratory scale models. Per. Pol. Civil Eng. 52: 63-71.
Ziou D, Tabbone S (1998). Edge detection
techniques-an overview. S MACH PERC 8: 537-559.
Zhang Y, Miao Z (2014). Object recognition
based on ORB and self-adaptive kernel clustering algorithm. 2014 12th International Conference on Signal Processing (ICSP). IEEE, 2014:1397-1402.
Xie YG, Wang Q, Chang, YX, Zhang, XY (2022). Fast Target Recognition Based on Improved ORB Feature. Appl. Sci 2022: 786.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Shujuan Wang, Shichao Lu, Jiaqi Liu, Miao Wang, Hongliang Luo, Jihong Shen, Shouxu Qiao, Yuntao Dai
This work is licensed under a Creative Commons Attribution 4.0 International License.
