Open Access iconOpen Access

ARTICLE

crossmark

Deep Learning Based Underground Sewer Defect Classification Using a Modified RegNet

Yu Chen1, Sagar A. S. M. Sharifuzzaman2, Hangxiang Wang1, Yanfen Li1, L. Minh Dang3, Hyoung-Kyu Song3, Hyeonjoon Moon1,*

1 Department of Computer Science and Engineering, Sejong University, Seoul, 05006, Korea
2 Department of Intelligent Mechatronics Engineering, Sejong University, Seoul, 05006, Korea
3 Department of Information of Communication Engineering, and Convergence Engineering for Intelligent Drone, Sejong University, Seoul, 05006, Korea

* Corresponding Author: Hyeonjoon Moon. Email: email

Computers, Materials & Continua 2023, 75(3), 5455-5473. https://doi.org/10.32604/cmc.2023.033787

Abstract

The sewer system plays an important role in protecting rainfall and treating urban wastewater. Due to the harsh internal environment and complex structure of the sewer, it is difficult to monitor the sewer system. Researchers are developing different methods, such as the Internet of Things and Artificial Intelligence, to monitor and detect the faults in the sewer system. Deep learning is a promising artificial intelligence technology that can effectively identify and classify different sewer system defects. However, the existing deep learning based solution does not provide high accuracy prediction and the defect class considered for classification is very small, which can affect the robustness of the model in the constraint environment. As a result, this paper proposes a sewer condition monitoring framework based on deep learning, which can effectively detect and evaluate defects in sewer pipelines with high accuracy. We also introduce a large dataset of sewer defects with 20 different defect classes found in the sewer pipeline. This study modified the original RegNet model by modifying the squeeze excitation (SE) block and adding the dropout layer and Leaky Rectified Linear Units (LeakyReLU) activation function in the Block structure of RegNet model. This study explored different deep learning methods such as RegNet, ResNet50, very deep convolutional networks (VGG), and GoogleNet to train on the sewer defect dataset. The experimental results indicate that the proposed system framework based on the modified-RegNet (RegNet+) model achieves the highest accuracy of 99.5 compared with the commonly used deep learning models. The proposed model provides a robust deep learning model that can effectively classify 20 different sewer defects and be utilized in real-world sewer condition monitoring applications.

Keywords


Cite This Article

APA Style
Chen, Y., Sharifuzzaman, S.A.S.M., Wang, H., Li, Y., Dang, L.M. et al. (2023). Deep learning based underground sewer defect classification using a modified regnet. Computers, Materials & Continua, 75(3), 5455-5473. https://doi.org/10.32604/cmc.2023.033787
Vancouver Style
Chen Y, Sharifuzzaman SASM, Wang H, Li Y, Dang LM, Song H, et al. Deep learning based underground sewer defect classification using a modified regnet. Comput Mater Contin. 2023;75(3):5455-5473 https://doi.org/10.32604/cmc.2023.033787
IEEE Style
Y. Chen et al., “Deep Learning Based Underground Sewer Defect Classification Using a Modified RegNet,” Comput. Mater. Contin., vol. 75, no. 3, pp. 5455-5473, 2023. https://doi.org/10.32604/cmc.2023.033787



cc Copyright © 2023 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1081

    View

  • 1276

    Download

  • 1

    Like

Share Link