Image processing for hydraulic jump free-surface detection: coupled gradient/machine learning model
Article (Accepted Version)
Metadata
Show full item recordAbstract
High-frequency oscillations and high surface aeration, induced by the strong turbulence, make water depth measurement for hydraulic jumps a persistently challenging task. The investigation of the hydraulic jump behaviour persists as an important research theme, especially with regards to the stilling basin design. Reliable knowledge of time-averaged and extreme values along a depth profile can help develop an adequate design of a stilling basin, improve safety and aid the understanding of the jump phenomenon. This paper presents an attempt of mitigating certain limitations of existing depth measurement methods by adopting a non-intrusive computer vision-based approach to measuring water depth profile of a hydraulic jump. The proposed method analyses video data in order to detect the boundary between the air-water mixture and the laboratory flume wall. This is achieved by coupling two computer vision methods: (1) analysis of the vertical image gradients, and (2) general-purpose edge det...ection using a deep neural network model. While the gradient analysis technique alone can provide adequate results, its performance can be significantly improved in combination with a neural network model which incorporates a "human-like" vision in the algorithm. The model coupling reduces the likelihood of false detections and improves the overall detection accuracy. The proposed method is tested in two experiments with different degrees of jump aeration. Results show that the coupled model can reliably and accurately capture the instantaneous depth profile along the jump, with low sensitivity to image noise and flow aeration. The coupled model presented fewer false detections than the gradient-based model, and offered consistent performance in regions of high, as well as low aeration. The proposed approach allows for automated detection of the free-surface interface and expands the potential of computer vision-based measurement methods in hydraulics.
Keywords:
hydraulic jump / depth measurement / stilling basins / non-intrusive measurement / computer vision / image processingSource:
Measurement Science and Technology, 2020Publisher:
- IOP
Funding / projects:
- Urban Drainage Systems as Key Infrastructure in Cities and Towns (RS-37010)
- Monitoring and Modeling of Rivers and Reservoirs (MORE) - Physical, Chemical, Biological and Morphodynamic Parameters (RS-37009)
DOI: 10.1088/1361-6501/ab8b22
ISSN: 0957-0233
WoS: 000553406700001
Scopus: 2-s2.0-85092624335
Collections
Institution/Community
GraFarTY - JOUR AU - Ljubičić, Robert AU - Vićanović, Ivana AU - Zindović, Budo AU - Kapor, Radomir AU - Savić, Ljubodrag PY - 2020 UR - https://grafar.grf.bg.ac.rs/handle/123456789/1976 AB - High-frequency oscillations and high surface aeration, induced by the strong turbulence, make water depth measurement for hydraulic jumps a persistently challenging task. The investigation of the hydraulic jump behaviour persists as an important research theme, especially with regards to the stilling basin design. Reliable knowledge of time-averaged and extreme values along a depth profile can help develop an adequate design of a stilling basin, improve safety and aid the understanding of the jump phenomenon. This paper presents an attempt of mitigating certain limitations of existing depth measurement methods by adopting a non-intrusive computer vision-based approach to measuring water depth profile of a hydraulic jump. The proposed method analyses video data in order to detect the boundary between the air-water mixture and the laboratory flume wall. This is achieved by coupling two computer vision methods: (1) analysis of the vertical image gradients, and (2) general-purpose edge detection using a deep neural network model. While the gradient analysis technique alone can provide adequate results, its performance can be significantly improved in combination with a neural network model which incorporates a "human-like" vision in the algorithm. The model coupling reduces the likelihood of false detections and improves the overall detection accuracy. The proposed method is tested in two experiments with different degrees of jump aeration. Results show that the coupled model can reliably and accurately capture the instantaneous depth profile along the jump, with low sensitivity to image noise and flow aeration. The coupled model presented fewer false detections than the gradient-based model, and offered consistent performance in regions of high, as well as low aeration. The proposed approach allows for automated detection of the free-surface interface and expands the potential of computer vision-based measurement methods in hydraulics. PB - IOP T2 - Measurement Science and Technology T1 - Image processing for hydraulic jump free-surface detection: coupled gradient/machine learning model DO - 10.1088/1361-6501/ab8b22 ER -
@article{ author = "Ljubičić, Robert and Vićanović, Ivana and Zindović, Budo and Kapor, Radomir and Savić, Ljubodrag", year = "2020", abstract = "High-frequency oscillations and high surface aeration, induced by the strong turbulence, make water depth measurement for hydraulic jumps a persistently challenging task. The investigation of the hydraulic jump behaviour persists as an important research theme, especially with regards to the stilling basin design. Reliable knowledge of time-averaged and extreme values along a depth profile can help develop an adequate design of a stilling basin, improve safety and aid the understanding of the jump phenomenon. This paper presents an attempt of mitigating certain limitations of existing depth measurement methods by adopting a non-intrusive computer vision-based approach to measuring water depth profile of a hydraulic jump. The proposed method analyses video data in order to detect the boundary between the air-water mixture and the laboratory flume wall. This is achieved by coupling two computer vision methods: (1) analysis of the vertical image gradients, and (2) general-purpose edge detection using a deep neural network model. While the gradient analysis technique alone can provide adequate results, its performance can be significantly improved in combination with a neural network model which incorporates a "human-like" vision in the algorithm. The model coupling reduces the likelihood of false detections and improves the overall detection accuracy. The proposed method is tested in two experiments with different degrees of jump aeration. Results show that the coupled model can reliably and accurately capture the instantaneous depth profile along the jump, with low sensitivity to image noise and flow aeration. The coupled model presented fewer false detections than the gradient-based model, and offered consistent performance in regions of high, as well as low aeration. The proposed approach allows for automated detection of the free-surface interface and expands the potential of computer vision-based measurement methods in hydraulics.", publisher = "IOP", journal = "Measurement Science and Technology", title = "Image processing for hydraulic jump free-surface detection: coupled gradient/machine learning model", doi = "10.1088/1361-6501/ab8b22" }
Ljubičić, R., Vićanović, I., Zindović, B., Kapor, R.,& Savić, L.. (2020). Image processing for hydraulic jump free-surface detection: coupled gradient/machine learning model. in Measurement Science and Technology IOP.. https://doi.org/10.1088/1361-6501/ab8b22
Ljubičić R, Vićanović I, Zindović B, Kapor R, Savić L. Image processing for hydraulic jump free-surface detection: coupled gradient/machine learning model. in Measurement Science and Technology. 2020;. doi:10.1088/1361-6501/ab8b22 .
Ljubičić, Robert, Vićanović, Ivana, Zindović, Budo, Kapor, Radomir, Savić, Ljubodrag, "Image processing for hydraulic jump free-surface detection: coupled gradient/machine learning model" in Measurement Science and Technology (2020), https://doi.org/10.1088/1361-6501/ab8b22 . .