Deep learning for automated encrustation detection in sewer inspection

被引:2
作者
Yusuf, Wasiu [1 ]
Alaka, Hafiz [1 ]
Ahmad, Mubashir [1 ]
Godoyon, Wusu [1 ]
Ajayi, Saheed [2 ]
Toriola-Coker, Luqman Olalekan [3 ]
Ahmed, Abdullahi [4 ]
机构
[1] Univ Hertfordshire, Big Data Technol & Innovat Lab, Hatfield AL10 9AB, England
[2] Leeds Beckett Univ, Sch Built Environm Engn & Comp, Leeds LS2 8AG, England
[3] Univ Salford, Sch Built Environm Engn & Comp, Manchester M5 4WT, England
[4] Coventry Univ, Sch Energy Construct & Environm, Coventry CV1 5FB, England
来源
INTELLIGENT SYSTEMS WITH APPLICATIONS | 2024年 / 24卷
基金
“创新英国”项目;
关键词
Deep-learning; Encrustation; CNN; Sewer systems; CCTV; DEFECT CLASSIFICATION; DAMAGE DETECTION; NEURAL-NETWORKS;
D O I
10.1016/j.iswa.2024.200433
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Rapid urbanization and population growth in recent decades have placed significant pressure on urban cities to rely heavily on underground infrastructure, such as sewers and tunnels, to maintain the provision of essential services. These sewers, typically having a limited lifespan of 50 to 100 years, are prone to various forms of defects. While prior research has primarily addressed common sewer defect like crack, root intrusion, and infiltration among others, the challenge of encrustation-the formation of hard deposits within sewer systems-has received less attention. This study presents a pioneering deep-learning approach to detect encrustation in sewers by leveraging survey videos from 14 different sewers in the United Kingdom. Our work marks the first effort to develop models specifically for detecting encrustation using deep learning techniques, as previous studies have focused on other types of deposits such as settled and attached deposits. By converting the videos into sequential image frames, we subjected them to thorough analysis and several image pre-processing techniques. Our contributions include the development and comparison of different classification models using backbone CNN networks such as AlexNet, VGG16, EfficientNet, and VGG19 to classify encrustation. Notably, this study provides the first metric-based comparison of these backbone networks to identify the most effective model for encrustation detection. The results demonstrate an impressive 96 % accuracy using the deep architecture of VGG19. Beyond accuracy, this research explores the impact of data augmentation and network dropout on reducing overfitting and enhancing model performance. Additionally, we analyze the time complexities associated with training models with and without data augmentation, providing valuable insights into the efficiency of our approach.
引用
收藏
页数:18
相关论文
共 50 条
[41]   Automatic Detection Method of Sewer Pipe Defects Using Deep Learning Techniques [J].
Zhang, Jiawei ;
Liu, Xiang ;
Zhang, Xing ;
Xi, Zhenghao ;
Wang, Shuohong .
APPLIED SCIENCES-BASEL, 2023, 13 (07)
[42]   Pill Detection Model for Medicine Inspection Based on Deep Learning [J].
Kwon, Hyuk-Ju ;
Kim, Hwi-Gang ;
Lee, Sung-Hak .
CHEMOSENSORS, 2022, 10 (01)
[43]   Wind Turbine Surface Damage Detection by Deep Learning Aided Drone Inspection Analysis [J].
Shihavuddin, A. S. M. ;
Chen, Xiao ;
Fedorov, Vladimir ;
Christensen, Anders Nymark ;
Riis, Nicolai Andre Brogaard ;
Branner, Kim ;
Dahl, Anders Bjorholm ;
Paulsen, Rasmus Reinhold .
ENERGIES, 2019, 12 (04)
[44]   Dual visual inspection for automated quality detection and printing optimization of two-photon polymerization based on deep learning [J].
Hu, Ningning ;
Ding, Lujia ;
Men, Lijun ;
Zhou, Wenju ;
Zhang, Wenjun ;
Yin, Ruixue .
JOURNAL OF INTELLIGENT MANUFACTURING, 2024,
[45]   Automated visual inspection of target parts for train safety based on deep learning [J].
Zhou, Fuqiang ;
Song, Ya ;
Liu, Liu ;
Zheng, Dongtian .
IET INTELLIGENT TRANSPORT SYSTEMS, 2018, 12 (06) :550-555
[46]   TNet: Power Pole Classification with Deep Learning for Automated Inspection in Smart Grids [J].
Gao, Zishuo ;
Gao, Ge ;
Liu, Chen ;
Xu, Yiteng ;
Liu, Chaopeng ;
Luo, Zhuang ;
Hu, Yi .
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2025,
[47]   Automated abnormalities detection in mammography using deep learning [J].
El-Banby, Ghada M. ;
Salem, Nourhan S. ;
Tafweek, Eman A. ;
Abd El-Azziz, Essam N. .
COMPLEX & INTELLIGENT SYSTEMS, 2024, 10 (05) :7279-7295
[48]   Automated Patient Discomfort Detection Using Deep Learning [J].
Ahmed, Imran ;
Khan, Iqbal ;
Ahmad, Misbah ;
Adnan, Awais ;
Aljuaid, Hanan .
CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 71 (02) :2559-2577
[49]   Efficacy of Deep Learning Approach for Automated Melanoma Detection [J].
Renjith, V. S. ;
Jose, P. Subha Hency .
2021 INTERNATIONAL CONFERENCE ON DECISION AID SCIENCES AND APPLICATION (DASA), 2021,
[50]   CardioXNet: Automated Detection for Cardiomegaly Based on Deep Learning [J].
Que, Qiwen ;
Tang, Ze ;
Wang, Ruoshi ;
Zeng, Zeng ;
Wang, Jie ;
Chua, Matthew ;
Gee, Teo Sin ;
Yang, Xulei ;
Veeravalli, Bharadwaj .
2018 40TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2018, :612-615