Author
C. T.M. Snaterse
Bio: C. T.M. Snaterse is an academic researcher. The author has contributed to research in topics: Sanitary sewer & Data quality. The author has an hindex of 1, co-authored 1 publications receiving 100 citations.
Topics: Sanitary sewer, Data quality
Papers
More filters
TL;DR: In this article, the authors assess the quality of the analysis of visual sewer inspection data by analysing data reproducibility; three types of capabilities to subjectively assess data are distinguished: the recognition of defects, the description of defects according to a prescribed coding system and the interpretation of sewer inspection reports.
Abstract: In common with most infrastructure systems, sewers are often inspected visually. Currently, the results from these inspections inform decisions for significant investments regarding sewer rehabilitation or replacement. In practice, the quality of the data and its analysis are not questioned although psychological research indicates that, as a consequence of the use of subjective analysis of the collected images, errors are inevitable. This article assesses the quality of the analysis of visual sewer inspection data by analysing data reproducibility; three types of capabilities to subjectively assess data are distinguished: the recognition of defects, the description of defects according to a prescribed coding system and the interpretation of sewer inspection reports. The introduced uncertainty is studied using three types of data: inspector examination results of sewer inspection courses, data gathered in day-to-day practice, and the results of repetitive interpretation of the inspection results. After a thorough analysis of the data it can be concluded that for all cases visual sewer inspection data proved poorly reproducible. For the recognition of defects, it was found that the probability of a false positive is in the order of a few percent, the probability of a false negative is in the order of 25%.
120 citations
Cited by
More filters
TL;DR: A framework that uses deep convoluted neural networks (CNNs) to classify multiple defects in sewer CCTV images to improve the speed, accuracy, and consistency of sewer defect reporting is presented.
174 citations
TL;DR: Due to the difficulty to discriminate the defects, the low-level defect classification accuracy still needs improvements, but the proposed network with hierarchical classification also demonstrated superior performance over traditional approaches.
110 citations
TL;DR: A brief review of the recent research accomplishments in the field of design, maintenance, life-cycle management, and optimisation of structures and infrastructures reported in papers published in Structure and Infrastructure Engineering (SIE) during the period 2005-2011 can be found in this paper.
Abstract: The optimal decisions to maintain or improve the reliability and functionality of structures and infrastructure systems can only be achieved through proper integrated management planning in a life-cycle comprehensive framework. Structure and Infrastructure Engineering (SIE) is an international journal dedicated to recent advances inmaintenance, management, and life-cycle performance of a wide range of infrastructures. The purpose of this article is to provide a brief review of the recent research accomplishments in the field of design, maintenance, life-cycle management, and optimisation of structures and infrastructures reported in papers published in SIE during the period 2005–2011. The papers are categorised under main topics and very briefly discussed.
95 citations
Norwegian University of Science and Technology1, University of Lyon2, Swiss Federal Institute of Aquatic Science and Technology3, SINTEF4, Delft University of Technology5, University of Tehran6, University of Los Andes7, RWTH Aachen University8, University of Coimbra9, Pontifical Xavierian University10
TL;DR: Sewer asset management gained momentum and importance in recent years due to economic considerations, since infrastructure maintenance and rehabilitation directly represent major investments as discussed by the authors. But it is still a relatively new area.
Abstract: Sewer asset management gained momentum and importance in recent years due to economic considerations, since infrastructure maintenance and rehabilitation directly represent major investments. Becau...
70 citations
TL;DR: A convolutional neural network is designed and applied to automatically detect the twelve most common defect types in a dataset of over 2 million CCTV images and it is determined that if the human operator is augmented with the CNN, this may reduce the required human labor by up to 60.5%.
68 citations