Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks

Abstract

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.

An Automatic Defect Detection System for Petrochemical Pipeline Based on Cycle-GAN and YOLO v5

“…With the development of deep learning technology, it has been widely used in video processing [ 14 , 15 , 16 , 17 ], water level calculation [ 18 , 19 ], pipeline semantic segmentation [ 20 , 21 , 22 ], and pipeline defect classification [ 23 , 24 ] in the field of pipeline detection. Hassan et al [ 25 ] adopted AlexNet [ 26 ] into pipeline defect detection and used the images edited from pipeline CCTV videos to form the training set for the model.…”

Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification

“…The field has, however, become more transparent as many have started to directly compare different methods on the same datasets, in an effort to offset the lack of public detection and segmentation datasets [17,36,34]. Recently, the field has also started investigating other parts of the sewer inspection process [30,32,17,[37][38][39][40][41], such as Haurum et al [37] proposing a multi-task classification approach for simultaneously classifying defects, water level, pipe material, and pipe shape, and Wang et al [30] proposed a framework to accurately determine the severity of defects related to the operation and maintenance of the pipes. The field has also adopted recent trends from the general computer vision field such as selfsupervised learning [39], synthetic data generation [25,24,[42][43][44], neural architecture search [45], and usage of the Transformer architecture [17,46], indicating that the automated sewer inspection field is catching up to the general computer vision domain.…”

Neural Network-Based Price Tag Data Analysis

“…To solve such problems, various algorithms and smart systems are used, for example, KNN [4] and NSGA-III [5]. However, in the modern world neural networks can be used to solve such problems, there are a lot of projects that use neural networks for different tasks: speaker verification [6], speech rehabilitation after speech organs surgical interventions [7], authorship identification [8], water level estimation in sewer pipes [9], determining the presence of lung cancer or diabetes in patients on the basis of symptoms [10,11], etc.…”