scholarly journals Measurement of Wastewater Discharge in Sewer Pipes Using Image Analysis

Water ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1771
Author(s):  
Hyon Ji ◽  
Sung Yoo ◽  
Bong-Jae Lee ◽  
Dan Koo ◽  
Jeong-Hee Kang
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Water Level ◽  
Low Cost ◽  
Water Levels ◽  
Boundary Line ◽  
Sewer Pipe ◽  
Flow Meters ◽  
Submerged Area ◽  
Boundary Lines

Generally, the amount of wastewater in sewerage pipes is measured using sensor-based devices such as submerged area velocity flow meters or non-contact flow meters. However, these flow meters do not provide accurate measurements because of impurities, corrosion, and measurement instability due to high turbidity. However, cameras have advantages such as their low cost, easy service, and convenient operation compared to the sensors. Therefore, in this study, we examined the following three methods for measuring the flow rate by capturing images inside of a sewer pipe using a camera and analyzing the images to calculate the water level: direct visual inspection and recording, image processing, and deep learning. The MATLAB image processing toolbox was used for analysis. The image processing found the boundary line by adjusting the contrast of the image or removing noise; a network to find the boundary line between wastewater and sewer pipe was created after training the image segmentation results and placing them into three categories using deep learning. From the recognized water levels, geometrical features were used to identify the boundary lines, and flow velocities and flow rates were calculated from Manning’s equation. Using direct inspection and image-processing techniques, boundary lines in images were detected at rates of 12% and 53%, respectively. Although the deep-learning model required training, it demonstrated 100% water-level detection, thereby proving to be the most advantageous method. Moreover, there is enough potential to increase the accuracy of deep learning, and it can be a possible replacement for existing flow measurement sensors.

Denoising of river surface photogrammetric DEMs using deep learning

2021 ◽  
Author(s):  
Radosław Szostak ◽  
Przemysław Wachniew ◽  
Mirosław Zimnoch ◽  
Paweł Ćwiąkała ◽  
Edyta Puniach ◽  
...  
Keyword(s):  
Higher Education ◽  
Deep Learning ◽  
Water Level ◽  
Water Surface ◽  
Research University ◽  
Static Characteristic ◽  
Water Levels ◽  
Training Dataset ◽  
Observation Data ◽  
Characteristic Points

<p>Unmanned Aerial Vehicles (UAVs) can be an excellent tool for environmental measurements due to their ability to reach inaccessible places and fast data acquisition over large areas. In particular drones may have a potential application in hydrology, as they can be used to create photogrammetric digital elevation models (DEM) of the terrain allowing to obtain high resolution spatial distribution of water level in the river to be fed into hydrological models. Nevertheless, photogrammetric algorithms generate distortions on the DEM at the water bodies. This is due to light penetration below the water surface and the lack of static characteristic points on water surface that can be distinguished by the photogrammetric algorithm. The correction of these disturbances could be achieved by applying deep learning methods. For this purpose, it is necessary to build a training dataset containing DEMs before and after water surfaces denoising. A method has been developed to prepare such a dataset. It is divided into several stages. In the first step a photogrammetric surveys and geodetic water level measurements are performed. The second one includes generation of DEMs and orthomosaics using photogrammetric software. Finally in the last one the interpolation of the measured water levels is done to obtain a plane of the water surface and apply it to the DEMs to correct the distortion. The resulting dataset was used to train deep learning model based on convolutional neural networks. The proposed method has been validated on observation data representing part of Kocinka river catchment located in the central Poland.</p><p>This research has been partly supported by the Ministry of Science and Higher Education Project “Initiative for Excellence – Research University” and Ministry of Science and Higher Education subsidy, project no. 16.16.220.842-B02 / 16.16.150.545.</p>

Precise ground-based GNSS-reflectometry water level measurements using multiple low-cost antennas

2020 ◽  
Author(s):  
David Purnell ◽  
Natalya Gomez ◽  
William Minarik ◽  
Gregory Langston
Keyword(s):  
Water Level ◽  
Low Cost ◽  
Multiple Antennas ◽  
Random Noise ◽  
Water Levels ◽  
Tropospheric Delay ◽  
Sources Of Error ◽  
Gnss Reflectometry ◽  
Water Level Measurements ◽  
Level Sensors

<p>GNSS-Reflectometry (GNSS-R) is a promising new technique to monitor water levels due to easier and cheaper installation of instruments in remote environments compared to traditional acoustic sensors or pressure gauges. GNSS stations that have been used for reflectometry purposes thus far are designed for monitoring land motion and may cost more than 10,000 USD each. We have found that a low-cost GNSS antenna and receiver (10 USD) can be used to make equally precise water level measurements, with an RMSE of a few centimeters when compared to a collocated acoustic sensor. However, an RMSE of less than one centimeter is typical for water level sensors and this level of accuracy is desired for research purposes. Two of the dominant sources of error in GNSS-R measurements are the effects of random noise in the Signal-to-Noise Ratio (SNR) data and tropospheric delay. Modelling work suggests that these sources of error can be reduced by using multiple low-cost antennas in the same location. In light of this, we have installed an experimental setup of antennas at various locations along the Saint Lawrence River and Initial results show that multiple antennas can be used to provide more precise measurements than a single antenna. Our installations of multiple antennas are less than 5% of the cost of stations that have been used in previous GNSS-R literature. Hence this approach could be applied to install a dense network of water level sensors along rivers, lakes or coastlines at a relatively low cost. We expect that this approach could also be applied to GNSS-R soil moisture or snow depth measurements.</p>

Low-cost river discharge measurements using a transparent velocity-head rod

2020 ◽  
Author(s):  
Aurélien Despax ◽  
Jérôme Le Coz ◽  
Francis Pernot ◽  
Alexis Buffet ◽  
Céline Berni
Keyword(s):  
Water Level ◽  
Low Cost ◽  
Electrical Contact ◽  
Field Tests ◽  
Water Levels ◽  
Water Level Fluctuations ◽  
Velocity Head ◽  
Low Velocity ◽  
Average Deviation ◽  
The Difference

<p>The common streamgauging methods (ADCP, current-meter or tracer dilution) generally require expensive equipment, with the notable exception of volumetric gaugings and floats, which are however often difficult to implement and limited to specific conditions. The following work aims at testing and validating a reliable, easy-to-deploy and low-cost gauging method, at a cost typically below 40 € each.<br><br>The “velocity-head rod” firstly described by Wilm and Storey (1944), made transparent by Fonstad et al. (2005) and improved by Pike et al. (2016) meets these objectives, for wading gauging with velocities greater than 20 cm/s typically. The 9.85 cm wide clear plastic rod is placed vertically across the stream to identify upstream and downstream water levels using adjustable rulers. The difference in level (or velocity head) makes it possible to calculate the average velocity over the vertical, using a semi-empirical calibration relationship.<br><br>Experiments carried out in INRAE’s hydraulic laboratory and in the field have enabled us to find a calibration relationship similar to that proposed by Pike et al. (2016) and confirm the optimal conditions of use. The average deviation to a reference discharge has been found to be close to 5 % except for very slow-flow conditions. The influence of the width of the rod on the velocity-head was studied in the laboratory. The uncertainty of the velocity due to the reading of water levels has been estimated. It increases at low velocity due to decreasing sensitivity, and increases at high velocities due to water level fluctuations that are difficult to average.<br><br>Several improvements were tested in order to facilitate and improve the measurement operations, without increasing the cost too much: magnetic ruler, removal of a graduated steel rule (expensive), plastic ruler with water level and velocity graduations, reading the depth with another ruler, spirit level, electrical contact (so the operator has not to bend to the surface of the water). An operational procedure and a spreadsheet for computing discharge are proposed. The method being extremely simple and quick to apply is well suited for rapid estimates of flow (instead of floats), training or demonstrations, citizen science programs or cooperation with services with limited resources.</p><p>Acknowledgments<strong>: </strong>The authors thank Q. Morice, J. Cousseau, Y. Longefay (DREAL) who were involved in this study by carrying out field tests.</p>

scholarly journals Early warning flood detector adopting camera by Sobel Canny edge detection algorithm method

2021 ◽  
Vol 22 (3) ◽  
pp. 1796
Author(s):  
Satryo B. Utomo ◽  
Januar Fery Irawan ◽  
Rizqi Renafasih Alinra
Keyword(s):  
Image Processing ◽  
Edge Detection ◽  
Water Level ◽  
Real Time ◽  
Early Warning ◽  
Detection System ◽  
Water Levels ◽  
Level Gauge ◽  
Canny Edge Detection ◽  
Canny Edge

Early warning of floods is an essential part of disaster management. Various automatic detectors have been developed in flood mitigation, including cameras. But reliability and accuracy have not been improved. Besides, the use of monitoring devices has been employed to monitor water levels in various water building facilities. The early warning flood detector was carried out with a sensor camera using an orange ball that floats near the water level gauge in a bounding box. This approach uses the integration of computer vision and image processing, namely digital image processing techniques, with Sobel Canny edge detection (SCED) algorithms to detect quickly and accurately water levels in real-time. After the water level is measured, a flood detection process is carried out based on the specified water level. According to the results of experiments in the laboratory, it has been shown that the proposed approach can detect objects accurately and fast in real-time. Besides, from the water level detection experiment, good results were obtained. Therefore, the object detection system and water level can be used as an efficient and accurate early detection system for flood disasters.

scholarly journals Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera

2021 ◽  
Vol 11 (20) ◽  
pp. 9691
Author(s):  
Nur Atirah Muhadi ◽  
Ahmad Fikri Abdullah ◽  
Siti Khairunniza Bejo ◽  
Muhammad Razif Mahadi ◽  
Ana Mijic
Keyword(s):  
Deep Learning ◽  
Water Level ◽  
River Water ◽  
Correlation Coefficient ◽  
Rank Order ◽  
Measurement Data ◽  
Strong Relationship ◽  
Semantic Segmentation ◽  
Water Levels ◽  
Surveillance Systems

The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and IoU metrics, and around 80% for boundary F1 score (BF score), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than the results from the SegNet network. Therefore, the DeepLabv3+ network was used for practical application using a set of images captured at five consecutive days in the study area. The segmentation result and water level markers extracted from light detection and ranging (LiDAR) data were overlaid to estimate river water levels and observe the water fluctuation. River water levels were predicted based on the elevation from the predefined markers. The proposed water level framework was evaluated according to Spearman’s rank-order correlation coefficient. The correlation coefficient was 0.91, which indicates a strong relationship between the estimated water level and observed water level. Based on these findings, it can be concluded that the proposed approach has high potential as an alternative monitoring system that offers water region information and water level estimation for flood management and related activities.

scholarly journals Maker Buoy Variants for Water Level Monitoring and Tracking Drifting Objects in Remote Areas of Greenland

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1254
Author(s):  
Daniel F. Carlson ◽  
Wayne J. Pavalko ◽  
Dorthe Petersen ◽  
Martin Olsen ◽  
Andreas E. Hass
Keyword(s):  
Open Source ◽  
Water Level ◽  
Low Cost ◽  
Management Strategies ◽  
Greenland Ice Sheet ◽  
Water Levels ◽  
Glacial Lake ◽  
Remote Areas ◽  
The North ◽  
Meltwater Runoff

Meltwater runoff from the Greenland Ice Sheet changes water levels in glacial lakes and can lead to glacial lake outburst flooding (GLOF) events that threaten lives and property. Icebergs produced at Greenland’s marine terminating glaciers drift into Baffin Bay and the North Atlantic, where they can threaten shipping and offshore installations. Thus, monitoring glacial lake water levels and the drift of icebergs can enhance safety and aid in the scientific studies of glacial hydrology and iceberg-ocean interactions. The Maker Buoy was originally designed as a low-cost and open source sensor to monitor surface ocean currents. The open source framework, low-cost components, rugged construction and affordable satellite data transmission capabilities make it easy to customize for environmental monitoring in remote areas and under harsh conditions. Here, we present two such Maker Buoy variants that were developed to monitor water level in an ice-infested glacial lake in southern Greenland and to track drifting icebergs and moorings in the Vaigat Strait (Northwest Greenland). We describe the construction of each design variant, methods to access data in the field without an internet connection, and deployments in Greenland in summer 2019. The successful deployments of each Maker Buoy variant suggest that they may also be useful in operational iceberg management strategies and in GLOF monitoring programs.

scholarly journals Vision-based system for the control and measurement of wastewater flow rate in sewer systems

2009 ◽  
Vol 60 (9) ◽  
pp. 2281-2289 ◽  
Author(s):  
L. S. Nguyen ◽  
B. Schaeli ◽  
D. Sage ◽  
S. Kayal ◽  
D. Jeanbourquin ◽  
...  
Keyword(s):  
Image Processing ◽  
Water Level ◽  
Water Levels ◽  
Combined Sewer Overflows ◽  
Web Based ◽  
Tier System ◽  
Crucial Information ◽  
Rain Events ◽  
Processing Techniques

Combined sewer overflows and stormwater discharges represent an important source of contamination to the environment. However, the harsh environment inside sewers and particular hydraulic conditions during rain events reduce the reliability of traditional flow measurement probes. In the following, we present and evaluate an in situ system for the monitoring of water flow in sewers based on video images. This paper focuses on the measurement of the water level based on image-processing techniques. The developed image-based water level algorithms identify the wall/water interface from sewer images and measure its position with respect to real world coordinates. A web-based user interface and a 3-tier system architecture enable the remote configuration of the cameras and the image-processing algorithms. Images acquired and processed by our system were found to reliably measure water levels and thereby to provide crucial information leading to better understand particular hydraulic behaviors. In terms of robustness and accuracy, the water level algorithm provided equal or better results compared to traditional water level probes in three different in situ configurations.

scholarly journals Precise water level measurements using low-cost GNSS antenna arrays

2021 ◽  
Vol 9 (3) ◽  
pp. 673-685
Author(s):  
David J. Purnell ◽  
Natalya Gomez ◽  
William Minarik ◽  
David Porter ◽  
Gregory Langston
Keyword(s):  
Water Level ◽  
Antenna Arrays ◽  
Tide Gauge ◽  
Low Cost ◽  
Satellite System ◽  
Water Levels ◽  
Optimum Number ◽  
Tide Gauges ◽  
Wide Range ◽  
Water Level Measurements

Abstract. We have developed a ground-based Global Navigation Satellite System Reflectometry (GNSS-R) technique for monitoring water levels with a comparable precision to standard tide gauges (e.g. pressure transducers) but at a fraction of the cost and using commercial products that are straightforward to assemble. As opposed to using geodetic-standard antennas that have been used in previous GNSS-R literature, we use multiple co-located low-cost antennas to retrieve water levels via inverse modelling of signal-to-noise ratio data. The low-cost antennas are advantageous over geodetic-standard antennas not only because they are much less expensive (even when using multiple antennas in the same location) but also because they can be used for GNSS-R analysis over a greater range of satellite elevation angles. We validate our technique using arrays of four antennas at three test sites with variable tidal forcing and co-located operational tide gauges. The root mean square error between the GNSS-R and tide gauge measurements ranges from 0.69–1.16 cm when using all four antennas at each site. We find that using four antennas instead of a single antenna improves the precision by 30 %–50 % and preliminary analysis suggests that four appears to be the optimum number of co-located antennas. In order to obtain precise measurements, we find that it is important for the antennas to track GPS, GLONASS and Galileo satellites over a wide range of azimuth angles (at least 140∘) and elevation angles (at least 30∘). We also provide software for analysing low-cost GNSS data and obtaining GNSS-R water level measurements.

Low-cost smartphone-based LIBS combined with deep learning image processing for accurate lithology recognition

2021 ◽  
Author(s):  
Xu Wang ◽  
Sha Chen ◽  
Mengfan Wu ◽  
Ruiqin Zheng ◽  
Zhuo Liu ◽  
...  
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Linear Array ◽  
Low Cost ◽  
Two Dimensional ◽  
Multichannel Detection

A low-cost and multi-channel smartphone-based spectrometer was developed for LIBS. As the CMOS detector is two-dimensional, simultaneous multichannel detection were achieved by coupling a linear array of fibres for light...

scholarly journals Development and Assessment of Water-Level Prediction Models for Small Reservoirs Using a Deep Learning Algorithm

Water ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 55
Author(s):  
Tsumugu Kusudo ◽  
Atsushi Yamamoto ◽  
Masaomi Kimura ◽  
Yutaka Matsuno
Keyword(s):  
Water Management ◽  
Deep Learning ◽  
Water Level ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Water Levels ◽  
Short Term ◽  
Term Memory ◽  
Deep Learning Algorithm ◽  
Long Short Term Memory

In this study, we aimed to develop and assess a hydrological model using a deep learning algorithm for improved water management. Single-output long short-term memory (LSTM SO) and encoder-decoder long short-term memory (LSTM ED) models were developed, and their performances were compared using different input variables. We used water-level and rainfall data from 2018 to 2020 in the Takayama Reservoir (Nara Prefecture, Japan) to train, test, and assess both models. The root-mean-squared error and Nash–Sutcliffe efficiency were estimated to compare the model performances. The results showed that the LSTM ED model had better accuracy. Analysis of water levels and water-level changes presented better results than the analysis of water levels. However, the accuracy of the model was significantly lower when predicting water levels outside the range of the training datasets. Within this range, the developed model could be used for water management to reduce the risk of downstream flooding, while ensuring sufficient water storage for irrigation, because of its ability to determine an appropriate amount of water for release from the reservoir before rainfall events.

Sign in / Sign up

Export Citation Format

Share Document