Color characteristics for the evaluation of suspended sediments

Moirogiorgou, Konstantia; Nerantzaki, Sofia D.; Livanos, George; Antonakakis, Marios; Nikolaidis, Nikolaos P.; Petrakis, Euripides G. M.; Savakis, Andreas; Giakos, George; Zervakis, Michalis; Mania, Katerina

doi:10.1109/ist.2015.7294574

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods are expensive and require precise in-situ imaging systems, like Video Plankton Recorder (VPR) (Davis et al, 2005) and Underwater Vision Profiler (UVP) (Gorsky et al, 2000;Picheral et al, 2010). The indirect methods, on the contrary, aim to determine the SPM concentration by analyzing specific image signals, such as the ratio between image hue and saturation (Moirogiorgou et al, 2015), the ratio of blue and red counts (Hoguane et al, 2012), or mean grey level value (Lunven et al, 2003). These methods don't require sophisticated imaging instrument, and only use a digital camera to capture images.…”

Section: Introductionmentioning

confidence: 99%

In-situ long-period monitoring of suspended particulate matter dynamics in deep sea with digital video images

Wang

Cong²,

Xia³

et al. 2022

Front. Mar. Sci.

View full text Add to dashboard Cite

Suspended particulate matter (SPM) plays an important role in material transport, deposition, resuspension and the function of benthic communities’ processes in deep sea. SPM concentration data is usually indirectly measured by optical/acoustic sensors. However, converting these sensors’ signal to SPM concentration is associated with a number of uncertainties, which will lead to mis-estimation of the results. Some researchers recommend combining several optical/acoustic sensors to determine SPM concentration. However, due to the lack of corresponding video images, the interpretation of significant mismatch signals recorded by different sensors is subjective. Consequently, a better understanding of long-period SPM dynamics, especially in deep sea, is still a challenge. In this study, we seek to monitor the dynamics of SPM in deep sea, by firstly obtaining in-situ digital video images at a water depth of 1450 m on the northern slope of South China Sea in 2020, and secondly developing a digital image processing method to process the in-situ monitoring data. In this method, we defined an image signal which was the ratio between the area of the SPM and that of the total image, to characterize the SPM concentration. A linear regression model of the image signal and SPM concentration was established (R2 = 0.72). K-fold cross-validation showed that the performance of the model was well. We calculated the SPM concentration derived from image signal, and manually classified SPM into three distinct morphological groups. The long-period observation revealed that numerous aggregates existed in deep sea. The change of SPM concentration and morphology under hydrodynamics was synchronous. When current speed equaled to or exceeded 0.15 m/s, there was a significantly increase in SPM concentration and size. However, such increase was episodic. When current speed decreased, they will also decrease. In addition, we compared the image signal with the optical/acoustic backscattering signal, analyzed the mismatch period among these three signals. We found that the optical backscatter signal can’t accurately reflect the SPM concentration during the mismatch period. To our best knowledge, this is the first time that the in-situ digital video images were used to analyze the dynamics of SPM in deep sea.

show abstract

Section: Introductionmentioning

confidence: 99%

In-situ long-period monitoring of suspended particulate matter dynamics in deep sea with digital video images

Wang

Cong²,

Xia³

et al. 2022

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

Continuous monitoring of suspended sediment concentrations using image analytics and deriving inherent correlations by machine learning

Ghorbani

Khatibi²,

Singh

et al. 2020

Sci Rep

View full text Add to dashboard Cite

The barriers for the development of continuous monitoring of Suspended Sediment Concentration (SSC) in channels/rivers include costs and technological gaps but this paper shows that a solution is feasible by: (i) using readily available high-resolution images; (ii) transforming the images into image analytics to form a modelling dataset; and (iii) constructing predictive models by learning inherent correlation between observed SSC values and their image analytics. High-resolution images were taken of water containing a series of SSC values using an exploratory flume. Machine learning is processed by dividing the dataset into training and testing sets and the paper uses the following models: Generalized Linear Machine (GLM) and Distributed Random Forest (DRF). Results show that each model is capable of reliable predictions but the errors at higher SSC are not fully explained by modelling alone. Here we offer sufficient evidence for the feasibility of a continuous SSC monitoring capability in channels before the next phase of the study with the goal of producing practice guidelines.

show abstract

Color characteristics for the evaluation of suspended sediments

Cited by 2 publications

References 5 publications

In-situ long-period monitoring of suspended particulate matter dynamics in deep sea with digital video images

In-situ long-period monitoring of suspended particulate matter dynamics in deep sea with digital video images

Continuous monitoring of suspended sediment concentrations using image analytics and deriving inherent correlations by machine learning

Contact Info

Product

Resources

About