Next Article in Journal
Materials and Technologies for the Tertiary Treatment of Produced Water Contaminated by Oil Impurities through Nonfibrous Deep-Bed Media: A Review
Previous Article in Journal
Impact of Nutrients, Temperatures, and a Heat Wave on Zooplankton Community Structure: An Experimental Approach
Article

Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks

Visual Analysis of People (VAP) Lab, Aalborg University, Rendsburggade 14, 9000 Aalborg, Denmark
*
Author to whom correspondence should be addressed.
Water 2020, 12(12), 3412; https://doi.org/10.3390/w12123412
Received: 16 October 2020 / Revised: 23 November 2020 / Accepted: 30 November 2020 / Published: 4 December 2020
(This article belongs to the Section Wastewater Treatment and Reuse)
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. View Full-Text
Keywords: sewer pipes; convolutional neural networks; random forests; water level; sewer inspection standards sewer pipes; convolutional neural networks; random forests; water level; sewer inspection standards
Show Figures

Figure 1

MDPI and ACS Style

Haurum, J.B.; Bahnsen, C.H.; Pedersen, M.; Moeslund, T.B. Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks. Water 2020, 12, 3412. https://doi.org/10.3390/w12123412

AMA Style

Haurum JB, Bahnsen CH, Pedersen M, Moeslund TB. Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks. Water. 2020; 12(12):3412. https://doi.org/10.3390/w12123412

Chicago/Turabian Style

Haurum, Joakim B.; Bahnsen, Chris H.; Pedersen, Malte; Moeslund, Thomas B. 2020. "Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks" Water 12, no. 12: 3412. https://doi.org/10.3390/w12123412

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop