Review on Computer Aided Sewer Pipeline Defect Detection and Condition Assessment

Moradi, Saeed; Zayed, Tarek; Golkhoo, Farzaneh

doi:10.3390/infrastructures4010010

Cited by 50 publications

(22 citation statements)

References 44 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Currently, the interpretation of closedcircuit television images to identify the types and locations of pipeline defects is mostly conducted manually, which is time-consuming and labour-intensive, and its accuracy is not very high. Therefore, the research on the automatic detection method of sewer pipe defects using computer deep learning technology is constantly developing, so that the sewer pipe defects can be detected more accurately and faster (Yang & Su 2008;Cheng & Wang 2018;Moradi et al 2019). In order to prevent ground subsidence caused by aging and poor sewers, the Ministry of Environment of South Korea proposes to conduct detailed investigations on areas where ground subsidence may occur.…”

Section: Robustnessmentioning

confidence: 99%

Evaluation of sewer network resilience index under the perspective of ground collapse prevention

Zhang

Park

2021

Water Science and Technology

View full text Add to dashboard Cite

Generally, when evaluating the resilience of infrastructure, the four properties of resilience robustness, rapidity, resources, and redundancy (4Rs) are widely considered. However, there is little research on the resilience assessment of sewer networks. Therefore, to establish a framework to evaluate sewer network resilience under the perspective of urban ground collapse prevention, this study considers the 13 second-level detailed indicators corresponding to the 4 first-level indicators (4Rs) based on literature reviews and experts' opinions. An analytic hierarchy process (AHP) is used to obtain relative weights of each indicator and a weighted sum method (WSM) is used to evaluate sewer network resilience index (SRI). The evaluation system was applied to 8 small blocks of selected drainage areas in Seoul, South Korea, and the SRI of 8 small blocks are computed. This study could help the sewer management department to make decisions and manage sewer network assets that enhance the resilience of the sewer networks.

show abstract

Section: Robustnessmentioning

confidence: 99%

Evaluation of sewer network resilience index under the perspective of ground collapse prevention

Zhang

Park

2021

Water Science and Technology

View full text Add to dashboard Cite

show abstract

“…Проте аналіз даних відеоінспеції є трудомістким процесом, а звіти про інспекцію можуть мати помилки внаслідок суб'єктивного фактору оператора. Тому останнім часом у світі активно ведуться дослідження і розробки спрямовані на автоматизацію процесу аналізу відео даних інспекції з використанням технології штучного інтелекту [1,2].…”

Section: вступunclassified

“…Аналіз рис. 6 показує, що запропонований метод навчання має переваги у порівнянні з традиційним методом навчання за метрикою F1 (2). При цьому найкращі результати забезпечує застосування на II етапі навчання контрастно-центрованої функції втрат (7).…”

Section: результати машинного навчанняunclassified

Багатоетапний Метод Глибинного Навчання З Попереднім Самонавчанням Для Класифікаційного Аналізу Дефектів Стічних Труб

Москаленко¹,

Зарецький²,

Moskalenko³

et al. 2021

reks

View full text Add to dashboard Cite

A machine learningsemi-supervised method was developed for the classification analysis of defects on the surface of the sewer pipe based on CCTV video inspection images. The aim of the research is the process of defect detection on the surface of sewage pipes. The subject of the research is a machine learning method for the classification analysis of sewage pipe defects on video inspection images under conditions of a limited and unbalanced set of labeled training data. A five-stage algorithm for classifier training is proposed. In the first stage, contrast training occurs using the instance-prototype contrast loss function, where the normalized Euclidean distance is used to measure the similarity of the encoded samples. The second step considers two variants of regularized loss functions – a triplet NCA function and a contrast-center loss function. The regularizing component in the second stage of training is used to penalize the rounding error of the output feature vector to a discrete form and ensures that the principle of information bottlenecking is implemented. The next step is to calculate the binary code of each class to implement error-correcting codes, but considering the structure of the classes and the relationships between their features. The resulting prototype vector of each class is used as a label of image for training using the cross-entropy loss function. The last stage of training conducts an optimization of the parameters of the decision rules using the information criterion to consider the variance of the class distribution in Hamming binary space. A micro-averaged metric F1, which is calculated on test data, is used to compare learning outcomes at different stages and within different approaches. The results obtained on the Sewer-ML open dataset confirm the suitability of the training method for practical use, with an F1 metric value of 0.977. The proposed method provides a 9 % increase in the value of the micro-averaged F1 metric compared to the results obtained using the traditional method.

show abstract

“…Заміна всієї стічної труби вимагає значних матеріальних витрат, може бути пов'язана зі значними земляними роботами і часто призводить до ускладнень дорожнього руху. Більш економним варіантом є ремонт пошкоджених труб шляхом відновлення, але для цього потрібно мати інформацію про їх актуальний функціональний стан [1]. Однак безпосередня інспекція стічних труб людиною у переважній більшості випадків значно ускладнена чи взагалі неможлива.…”

Section: вступunclassified

Модель Та Метод Навчання Для Класифікаційного Аналізу Рівня Води В Стічних Трубах За Даними Відео Інспекції

Москаленко¹,

Зарецький²,

Коробов³

et al. 2021

reks

View full text Add to dashboard Cite

Models and training methods for water-level classification analysis on the footage of sewage pipe inspections have been developed and investigated. The object of the research is the process of water-level recognition, considering the spatial and temporal context during the inspection of sewage pipes. The subject of the research is a model and machine learning method for water-level classification analysis on video sequences of pipe inspections under conditions of limited size and an unbalanced set of training data. A four-stage algorithm for training the classifier is proposed. At the first stage of training, training occurs with a softmax triplet loss function and a regularizing component to penalize the rounding error of the network output to a binary code. The next step is to define a binary code (reference vector) for each class according to the principles of error-correcting output codes, but considering the intraclass and interclass relations. The computed reference vector of each class is used as the target label of the sample for further training using the joint cross-entropy loss function. The last stage of machine learning involves optimizing the parameters of the decision rules based on the information criterion to account for the boundaries of deviation of the binary representation of the observations of each class from the corresponding reference vectors. As a classifier model, a combination of 2D convolutional feature extractor for each frame and temporal network to analyze inter-frame dependencies is considered. The different variants of the temporal network are compared. We consider a 1D regular convolutional network with dilated convolutions, 1D causal convolutional network with dilated convolutions, recurrent LSTM-network, recurrent GRU-network. The performance of the models is compared by the micro-averaged metric F1 computed on the test subset. The results obtained on the dataset from Ace Pipe Cleaning (Kansas City, USA) confirm the suitability of the model and training method for practical use, the obtained value of F1-metric is 0.88. The results of training by the proposed method were compared with the results obtained using the traditional method. It was shown that the proposed method provides a 9 % increase in the value of micro-averaged F1-measure.

show abstract

Review on Computer Aided Sewer Pipeline Defect Detection and Condition Assessment

Cited by 50 publications

References 44 publications

Evaluation of sewer network resilience index under the perspective of ground collapse prevention

Evaluation of sewer network resilience index under the perspective of ground collapse prevention

Багатоетапний Метод Глибинного Навчання З Попереднім Самонавчанням Для Класифікаційного Аналізу Дефектів Стічних Труб

Модель Та Метод Навчання Для Класифікаційного Аналізу Рівня Води В Стічних Трубах За Даними Відео Інспекції

Contact Info

Product

Resources

About