TY  - GEN
AU  - Ljubičić, Robert
AU  - Vićanović, Ivana
AU  - Zindović, Budo
AU  - Kapor, Radomir
AU  - Savić, Ljubodrag
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3035
T1  - Hydraulic jump free-surface detection using image processing - детекција слободне површине хидрауличког скока путем метода обраде слика [техничко решење]
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3035
ER  - 

@misc{
author = "Ljubičić, Robert and Vićanović, Ivana and Zindović, Budo and Kapor, Radomir and Savić, Ljubodrag",
year = "2022",
title = "Hydraulic jump free-surface detection using image processing - детекција слободне површине хидрауличког скока путем метода обраде слика [техничко решење]",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3035"
}

Ljubičić, R., Vićanović, I., Zindović, B., Kapor, R.,& Savić, L.. (2022). Hydraulic jump free-surface detection using image processing - детекција слободне површине хидрауличког скока путем метода обраде слика [техничко решење]. .
https://hdl.handle.net/21.15107/rcub_grafar_3035

Ljubičić R, Vićanović I, Zindović B, Kapor R, Savić L. Hydraulic jump free-surface detection using image processing - детекција слободне површине хидрауличког скока путем метода обраде слика [техничко решење]. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_3035 .

Ljubičić, Robert, Vićanović, Ivana, Zindović, Budo, Kapor, Radomir, Savić, Ljubodrag, "Hydraulic jump free-surface detection using image processing - детекција слободне површине хидрауличког скока путем метода обраде слика [техничко решење]" (2022),
https://hdl.handle.net/21.15107/rcub_grafar_3035 .

TY  - 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 . .

TY  - JOUR
AU  - Marjanović, Dušan
AU  - Vićanović, Ivana
AU  - Ljubičić, Robert
AU  - Zindović, Budo
AU  - Savić, Ljubodrag
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1867
AB  - Određivanje i praćenje promena nivoa vode u laboratorijskim uslovima primenom tradicionalnih mernih metoda opterećeno je raznim nedostacima: tačnost, frekvencija uzorkovanja, inertnost mernog uređaja i osetljivost na spoljne faktore. U cilju prevazilaženja navedenih nedostataka predlaže se alternativna metoda, zasnovana na tehnikama obrade slika iz video zapisa laboratorijskog eksperimenta. Pored opisa metodologije i njene primene na model vodostana pri brzim oscilacijama nivoa, ovaj rad prikazuje i poređenje dobijenih rezultata merenja sa dve tradicionalne metode: (1) ultražvučno merenje udaljenosti, i (2) merenje pritiska u tački. Pokazano je da je predložena metoda uporedive tačnosti, da ima niži nivo šuma i da je manje osetljiva na uticaj spoljnih faktora. Zbog svega navedenog, prikazana metoda može se koristiti kao adekvatna alternativa klasičnim mernim tehnikama u laboratorijskim uslovima.
PB  - Srpsko društo za odvodnjavanje i navodnjavanje
T2  - Vodoprivreda
T1  - Detekcija nivoa u laboratorijskim kanalima primenom tehnike obrade slika
IS  - 300-302
VL  - 51
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1867
ER  - 

@article{
author = "Marjanović, Dušan and Vićanović, Ivana and Ljubičić, Robert and Zindović, Budo and Savić, Ljubodrag",
year = "2019",
abstract = "Određivanje i praćenje promena nivoa vode u laboratorijskim uslovima primenom tradicionalnih mernih metoda opterećeno je raznim nedostacima: tačnost, frekvencija uzorkovanja, inertnost mernog uređaja i osetljivost na spoljne faktore. U cilju prevazilaženja navedenih nedostataka predlaže se alternativna metoda, zasnovana na tehnikama obrade slika iz video zapisa laboratorijskog eksperimenta. Pored opisa metodologije i njene primene na model vodostana pri brzim oscilacijama nivoa, ovaj rad prikazuje i poređenje dobijenih rezultata merenja sa dve tradicionalne metode: (1) ultražvučno merenje udaljenosti, i (2) merenje pritiska u tački. Pokazano je da je predložena metoda uporedive tačnosti, da ima niži nivo šuma i da je manje osetljiva na uticaj spoljnih faktora. Zbog svega navedenog, prikazana metoda može se koristiti kao adekvatna alternativa klasičnim mernim tehnikama u laboratorijskim uslovima.",
publisher = "Srpsko društo za odvodnjavanje i navodnjavanje",
journal = "Vodoprivreda",
title = "Detekcija nivoa u laboratorijskim kanalima primenom tehnike obrade slika",
number = "300-302",
volume = "51",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1867"
}

Marjanović, D., Vićanović, I., Ljubičić, R., Zindović, B.,& Savić, L.. (2019). Detekcija nivoa u laboratorijskim kanalima primenom tehnike obrade slika. in Vodoprivreda
Srpsko društo za odvodnjavanje i navodnjavanje., 51(300-302).
https://hdl.handle.net/21.15107/rcub_grafar_1867

Marjanović D, Vićanović I, Ljubičić R, Zindović B, Savić L. Detekcija nivoa u laboratorijskim kanalima primenom tehnike obrade slika. in Vodoprivreda. 2019;51(300-302).
https://hdl.handle.net/21.15107/rcub_grafar_1867 .

Marjanović, Dušan, Vićanović, Ivana, Ljubičić, Robert, Zindović, Budo, Savić, Ljubodrag, "Detekcija nivoa u laboratorijskim kanalima primenom tehnike obrade slika" in Vodoprivreda, 51, no. 300-302 (2019),
https://hdl.handle.net/21.15107/rcub_grafar_1867 .

TY  - CONF
AU  - Ljubičić, Robert
AU  - Vićanović, Ivana
AU  - Zindović, Budo
AU  - Kapor, Radomir
AU  - Savić, Ljubodrag
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1868
AB  - Hydraulic jumps exhibit a high degree of free-surface oscillations, triggered by intense turbulence and aeration.
These processes are difficult to model numerically and are frequently investigated on a scale model. However,
measuring the oscillatory characteristics of the hydraulic jump is not without issues, as the majority of available
methods are not intended for tracking instantaneous depth profile or free-surface interface (FSI). Some methods
are limited to a selected set of few predetermined points, and are sensitive to variations of secondary
characteristics of the hydraulic jump: point gauges are sensitive to aeration rate and rate of the free-surface
changes, electroconductive and optical probes require direct contact with the air-water mixture (disrupting the
free surface), while the ultrasonic distance measurement accuracy is severely impacted by the shape of the
free surface and aeration rate. To alleviate these issues, we propose the application of the non-intrusive method
based on image processing techniques to detect the instantaneous FSI. The first step is to record the freesurface region in a series of images, with a predefined constant time shift. Subsequently, the FSI along the
hydraulic jump is detected in every image. Presented method was used to reconstruct temporal evolution of the
depth profile from the FSI position in the recorded images. The obtained dominant FSI oscillation frequencies
along the hydraulic jump show good agreement with previous research. Results also show that the proposed
approach is more robust than previously available methods – minor sensitivity to camera shooting angle, rate
of the free-surface change, surface aeration variability, etc. Method is also very simple, with only a few tunable
parameters, and affordable, as the only required equipment is a camera. The preprocessing and calibration
steps needed to obtain reliable data for further processing are also described. Using method presented in this
paper, one can gain a better understanding of the characteristics of the hydraulic jump: instantaneous and timeaveraged FSI profile, as well as the frequency spectrum of FSI variations along the hydraulic jump. This can be
useful for the design of hydraulic structures, in particular – the hydraulic jump stilling basins.
PB  - IAHR
C3  - E-proceedings of the 38th IAHR World Congress
T1  - Image Processing for Hydraulic Jump Free-Surface Detection
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1868
ER  - 

@conference{
author = "Ljubičić, Robert and Vićanović, Ivana and Zindović, Budo and Kapor, Radomir and Savić, Ljubodrag",
year = "2019",
abstract = "Hydraulic jumps exhibit a high degree of free-surface oscillations, triggered by intense turbulence and aeration.
These processes are difficult to model numerically and are frequently investigated on a scale model. However,
measuring the oscillatory characteristics of the hydraulic jump is not without issues, as the majority of available
methods are not intended for tracking instantaneous depth profile or free-surface interface (FSI). Some methods
are limited to a selected set of few predetermined points, and are sensitive to variations of secondary
characteristics of the hydraulic jump: point gauges are sensitive to aeration rate and rate of the free-surface
changes, electroconductive and optical probes require direct contact with the air-water mixture (disrupting the
free surface), while the ultrasonic distance measurement accuracy is severely impacted by the shape of the
free surface and aeration rate. To alleviate these issues, we propose the application of the non-intrusive method
based on image processing techniques to detect the instantaneous FSI. The first step is to record the freesurface region in a series of images, with a predefined constant time shift. Subsequently, the FSI along the
hydraulic jump is detected in every image. Presented method was used to reconstruct temporal evolution of the
depth profile from the FSI position in the recorded images. The obtained dominant FSI oscillation frequencies
along the hydraulic jump show good agreement with previous research. Results also show that the proposed
approach is more robust than previously available methods – minor sensitivity to camera shooting angle, rate
of the free-surface change, surface aeration variability, etc. Method is also very simple, with only a few tunable
parameters, and affordable, as the only required equipment is a camera. The preprocessing and calibration
steps needed to obtain reliable data for further processing are also described. Using method presented in this
paper, one can gain a better understanding of the characteristics of the hydraulic jump: instantaneous and timeaveraged FSI profile, as well as the frequency spectrum of FSI variations along the hydraulic jump. This can be
useful for the design of hydraulic structures, in particular – the hydraulic jump stilling basins.",
publisher = "IAHR",
journal = "E-proceedings of the 38th IAHR World Congress",
title = "Image Processing for Hydraulic Jump Free-Surface Detection",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1868"
}

Ljubičić, R., Vićanović, I., Zindović, B., Kapor, R.,& Savić, L.. (2019). Image Processing for Hydraulic Jump Free-Surface Detection. in E-proceedings of the 38th IAHR World Congress
IAHR..
https://hdl.handle.net/21.15107/rcub_grafar_1868

Ljubičić R, Vićanović I, Zindović B, Kapor R, Savić L. Image Processing for Hydraulic Jump Free-Surface Detection. in E-proceedings of the 38th IAHR World Congress. 2019;.
https://hdl.handle.net/21.15107/rcub_grafar_1868 .

Ljubičić, Robert, Vićanović, Ivana, Zindović, Budo, Kapor, Radomir, Savić, Ljubodrag, "Image Processing for Hydraulic Jump Free-Surface Detection" in E-proceedings of the 38th IAHR World Congress (2019),
https://hdl.handle.net/21.15107/rcub_grafar_1868 .