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

Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks

Sewer pipe inspections are currently conducted by professionals who remotely control a robot from above ground. This expensive and slow approach is prone to human mistakes. Therefore, there is both an economic and scientific interest in automating the inspection process by creating systems able to recognize sewer defects. However, the extent of research put into automatic water level estimation in sewers has been limited despite being a prerequisite for further analysis of the pipe as only sections above the water level can be visually inspected. In this work, we utilize a dataset of still images obtained from over 5000 inspections carried out for three different Danish water utilities companies. This dataset is used for training and testing decision tree methods and convolutional neural networks (CNNs) for automatic water level estimation. We pose the estimation problem as a classification and regression problem, and compare the results of both approaches. Furthermore, we compare the effect of using different inspection standards for labeling the ground truth water level. By treating the problem as a classification task and using the 2015 Danish sewer inspection standard, where water levels are clustered based on visual appearance, we achieve an averaged F1 score of 79.29% using a fine-tuned ResNet-50 CNN. This shows the potential of using CNNs for water level estimation. We believe including temporal and contextual information will improve the results further.

Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data

Reference objects in video images can be used to indicate urban waterlogging depths. The detection of reference objects is the key step to obtain waterlogging depths from video images. Object detection models with convolutional neural networks (CNNs) have been utilized to detect reference objects. These models require a large number of labeled images as the training data to ensure the applicability at a city scale. However, it is hard to collect a sufficient number of urban flooding images containing valuable reference objects, and manually labeling images is time-consuming and expensive. To solve the problem, we present a method to synthesize image data as the training data. Firstly, original images containing reference objects and original images with water surfaces are collected from open data sources, and reference objects and water surfaces are cropped from these original images. Secondly, the reference objects and water surfaces are further enriched via data augmentation techniques to ensure the diversity. Finally, the enriched reference objects and water surfaces are combined to generate a synthetic image dataset with annotations. The synthetic image dataset is further used for training an object detection model with CNN. The waterlogging depths are calculated based on the reference objects detected by the trained model. A real video dataset and an artificial image dataset are used to evaluate the effectiveness of the proposed method. The results show that the detection model trained using the synthetic image dataset can effectively detect reference objects from images, and it can achieve acceptable accuracies of waterlogging depths based on the detected reference objects. The proposed method has the potential to monitor waterlogging depths at a city scale.

Automatic Estimation of Urban Waterlogging Depths from Video Images Based on Ubiquitous Reference Objects

Video supervision equipment, which is readily available in most cities, can record the processes of urban floods in video form. Ubiquitous reference objects, which often appear in videos, can be used to indicate urban waterlogging depths. This makes video images a valuable data source for obtaining waterlogging depths. However, the urban waterlogging information contained in video images has not been effectively mined and utilized. In this paper, we present a method to automatically estimate urban waterlogging depths from video images based on ubiquitous reference objects. First, reference objects from video images are detected during the flooding and non-flooding periods using an object detection model with a convolutional neural network (CNN). Then, waterlogging depths are estimated using the height differences between the detected reference objects in these two periods. A case study is used to evaluate the proposed method. The results show that our proposed method could effectively mine and utilize urban waterlogging depth information from video images. This method has the advantages of low economic cost, acceptable accuracy, high spatiotemporal resolution, and wide coverage. It is feasible to promote this proposed method within cities to monitor urban floods.

Implementation of an IoT Based Radar Sensor Network for Wastewater Management

Critical wastewater events such as sewer main blockages or overflows are often not detected until after the fact. These events can be costly, from both an environmental impact and monetary standpoint. A standalone, portable radar device allowing non-invasive benchmarking of sewer pumping station (SPS) pumps is presented. Further, by configuring and deploying a complete Low Power Wide Area Network (LPWAN), Shoalhaven Water (SW) now has the opportunity to create "Internet of Things" (IoT)-capable devices that offer freedom from the reliance on mobile network providers, whilst avoiding congestion on the existing Supervisory Control and Data Acquisition (SCADA) telemetry backbone. This network infrastructure allows for devices capable of real-time monitoring to alert of any system failures, providing an effective tool to proactively capture the current state of the sewer network between the much larger SPSs. This paper presents novel solutions to improve the current wastewater network management procedures employed by SW. This paper also offers a complete review of wastewater monitoring networks and is one of the first to offer robust testing of Long Range Wide Area Network (LoRaWAN) network capabilities in Australia. The paper also provides a comprehensive summary of the LoRa protocol and all its functions. It was found that a LPWAN, utilising the LoRaWAN protocol and deployed appropriately within a geographic area, can attain maximum transmission distances of 20 km within an urban environment and up to 35 km line of sight.

Measuring Inundation Depth in a Subway Station Using the Laser Image Analysis Method

Subway station platforms are vulnerable to flood damage. Thus, investigation of inundation properties in subway platforms is required to ensure the safety of citizens against flooding. In this study, the evacuation time and safety were analyzed in a subway station model using inundation depth measurements. The subway station model contained shallow water depth conditions, which did not allow for contact-type measurement devices. Instead, an image analysis procedure using laser images was proposed to measure the inundation depth. The proposed laser image analysis method can recognize a boundary line between the water and air by visualizing the water surface using a laser sheet. The inundation depth measurements using the image analysis method were reasonably accurate, resulting in differences of 2.97–7.67% compared to the results obtained using a digital point gauge. When inflow positions and flowrates of rainwater were changed, the measured results showed that the inundation depth increased in areas in which the rainwater inflow was relatively small or collided when moving in the direction opposite to the rainwater. The calculated evacuation time from the subway station showed that a drainage system is required to decrease the inundation depth in areas of inflowing rainwater collision. Furthermore, the estimated results of evacuation safety showed that safety handles are necessary even in low depth regions to prevent people from falling down due to increased flow velocity, during evacuation.

Uncertainty Comparison of Visual Sensing in Adverse Weather Conditions

This paper focuses on flood-region detection using monitoring images. However, adverse weather affects the outcome of image segmentation methods. In this paper, we present an experimental comparison of an outdoor visual sensing system using region-growing methods with two different growing rules—namely, GrowCut and RegGro. For each growing rule, several tests on adverse weather and lens-stained scenes were performed, taking into account and analyzing different weather conditions with the outdoor visual sensing system. The influence of several weather conditions was analyzed, highlighting their effect on the outdoor visual sensing system with different growing rules. Furthermore, experimental errors and uncertainties obtained with the growing rules were compared. The segmentation accuracy of flood regions yielded by the GrowCut, RegGro, and hybrid methods was 75%, 85%, and 87.7%, respectively.

Cyber surveillance for flood disasters

Regional heavy rainfall is usually caused by the influence of extreme weather conditions. Instant heavy rainfall often results in the flooding of rivers and the neighboring low-lying areas, which is responsible for a large number of casualties and considerable property loss. The existing precipitation forecast systems mostly focus on the analysis and forecast of large-scale areas but do not provide precise instant automatic monitoring and alert feedback for individual river areas and sections. Therefore, in this paper, we propose an easy method to automatically monitor the flood object of a specific area, based on the currently widely used remote cyber surveillance systems and image processing methods, in order to obtain instant flooding and waterlogging event feedback. The intrusion detection mode of these surveillance systems is used in this study, wherein a flood is considered a possible invasion object. Through the detection and verification of flood objects, automatic flood risk-level monitoring of specific individual river segments, as well as the automatic urban inundation detection, has become possible. The proposed method can better meet the practical needs of disaster prevention than the method of large-area forecasting. It also has several other advantages, such as flexibility in location selection, no requirement of a standard water-level ruler, and a relatively large field of view, when compared with the traditional water-level measurements using video screens. The results can offer prompt reference for appropriate disaster warning actions in small areas, making them more accurate and effective.

Non-contact assessment of COD and turbidity concentrations in water using diffuse reflectance UV-Vis spectroscopy

Water contamination is an important environmental concern underlining the need for reliable real-time information on contaminant concentrations in natural waters. Here, a new non-contact UV-Vis spectroscopic approach for monitoring contaminants in water, and especially wastewater, is proposed. Diffuse reflectance UV-Vis spectroscopy was applied to measure simultaneously the chemical oxygen demand (COD) and turbidity (TUR) concentrations in water. The measurements were carried out in the wavelength range from 200-1100 nm. The measured spectra were analysed using partial-least-squares (PLS) regression. The correlation coefficient between the measured and the reference concentrations of COD and TUR in the water samples were R(2) = 0.85 and 0.96, respectively. These results highlight the potential of non-contact UV-Vis spectroscopy for the assessment of water contamination. A system built on the concept would be able to monitor wastewater pollution continuously, without the need for laborious sample collection and subsequent laboratory analysis. Furthermore, since no parts of the system are in contact with the wastewater stream the need for maintenance is minimised.