A Review of Turbidity Detection Based on Computer Vision

Liu, Yeqi; Chen, Yingyi; Fang, Xiaomin

doi:10.1109/access.2018.2875071

Cited by 32 publications

(24 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the model herein presented is based on image quality distortion. Recently, alternative prediction methods have also been proposed (Liu et al 2018). In line with our main goal these methods may improve predictive capacity of mobile devices.…”

Section: Discussionmentioning

confidence: 97%

The effect of mobile camera selection on the capacity to predict water turbidity

Villamil

Victorino

Gómez

2021

Water Science and Technology

View full text Add to dashboard Cite

Recently, cameras of mobile phones emerged as an alternative for quantifying water turbidity. Most of these studies lack a strategy to determine the water turbidity for new samples, focusing mainly on one particular device. Nevertheless, widespread use of these approaches requires a predictive capacity on out-of-the-sample images acquired in devices of different capabilities. We studied the influence of mobile device camera sensors on the predictive performance of water turbidity for non-previously observed turbid images. For this, a reference database with turbid images acquired for different mobile devices was constructed. A machine learning method based on image quality measures and linear classifiers (least squares and LASSO) was proposed to perform predictions on each mobile device. Relative accuracy and precision were evaluated. Results suggest that these approaches may provide accurate predictions reaching most than 80% of relative accuracy with high test-retest reliability (>.99). Nevertheless, our results also indicate that the predictive performance levels dropped in low capacity quality sensors. Therefore, despite the high performance that can be reached using these approaches, widespread use on multiple mobile devices may require further developments of low-quality sensors and a better understanding of their operative ranges.

show abstract

Section: Discussionmentioning

confidence: 97%

The effect of mobile camera selection on the capacity to predict water turbidity

Villamil

Victorino

Gómez

2021

Water Science and Technology

View full text Add to dashboard Cite

show abstract

“…The decision to use a simple computer vision method in this case limits the workflow's application to solute/ solvent systems that meet the expectations of relatively clear solvent and bright solid. While more sophisticated computer vision methods for measuring turbidity exist (Liu et al, 2018), they typically rely on a standard comparison library that must be hand-built, requiring significant investment in time on the part of a human researcher as well as specialized laboratory equipment. Using a far simpler method in this case allowed us to demonstrate the validity of the automated solubility workflow using the simplest variant of the computer vision module.…”

Section: Computer Visionmentioning

confidence: 99%

Automated solubility screening platform using computer vision

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Different authors highlight the potential of satellite images in estimating different variables to determine water quality in wetlands and coastal zones [23][24][25][26][27][28], and most agree that one of the most effective methods for estimating the concentration of water quality parameters is through a combination of remote sensing and data sampled directly from the water bodies in question.…”

Section: State Of the Artmentioning

confidence: 99%

Landsat-7 ETM+ Based Remote Sensing as a Tool for Assessing Lakes Water Quality Characteristics

Cabezas-Alzate¹,

Garcés-Gómez²,

Céspedes³

2021

Journal of Southwest Jiaotong University

View full text Add to dashboard Cite

The article describes a new method using remote sensing techniques to set the mathematical models that allow the estimation of the most relevant parameters for water quality monitored in Laguna de Sonso lake, Valle del Cauca, determined using Landsat-7 ETM+ multispectral images. Chlorophyll-a (Chl-a), Turbidity, Dissolved Oxygen (DO), and Total Phosphorus (P) are the parameters chosen for this study. The annual dry and wet seasons were defined, from 2010 to 2017, with a total of 70 images. It was necessary to carry out a process of masking the water Buchón (Eichhornia crassipes) and replacing pixels using the statistical average of the two established annual seasons. For the case of Chl-a, the NDI ratio between the red and near-infrared (NIR) bands was the best correlated with an ; for turbidity, a regression with the red band, with an ; for DO, the ratio with the highest correlation was a simple ratio (SR) between the green and blue bands, with an ; and for P, a regression of the NIR band was enough, presenting an . Finally, the adjusted mathematical models were obtained for each established parameter, allowing the estimation of each parameter to monitor the lagoon water quality using images from the ETM+ sensor.

show abstract

A Review of Turbidity Detection Based on Computer Vision

Cited by 32 publications

References 61 publications

The effect of mobile camera selection on the capacity to predict water turbidity

The effect of mobile camera selection on the capacity to predict water turbidity

Automated solubility screening platform using computer vision

Landsat-7 ETM+ Based Remote Sensing as a Tool for Assessing Lakes Water Quality Characteristics

Contact Info

Product

Resources

About