Smart City Gnosys

Smart city article details

Title	A Deep Learning Based Automated Structural Defect Detection System For Sewer Pipelines
ID_Doc	1344
Authors	Kumar S.S.; Abraham D.M.
Year	2019
Published	Computing in Civil Engineering 2019: Smart Cities, Sustainability, and Resilience - Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2019
DOI	http://dx.doi.org/10.1061/9780784482445.029
Abstract	Automated interpretation of closed-circuit television (CCTV) inspection videos has the potential to improve the speed, accuracy, and consistency of sewer pipeline condition assessment. Previous approaches have focused on defect classification in images, with little focus on defect localization (i.e., calculating location of defects relative to the pipe). Recent studies have shown that deep-learning based object detection models can be used to classify and localize operational defects, such as roots and deposits; however, the detection of structural defects, such as pipe fractures is challenging, given their fine silhouettes in images. This paper presents a two-step defect detection framework that uses a 5-layered convolutional neural network (CNN) for classification followed by the you-only-look-once (YOLO) model for detection of pipe fractures. The framework was trained using 1,800 images and yielded a 0.71 average precision (AP) score in detecting fractures, when tested on 300 images. The proposed framework can also achieve a significant reduction in time taken to process CCTV videos. Ongoing research aims to validate the framework on videos from a variety of pipes and extend the framework to defect additional defect categories. © 2019 American Society of Civil Engineers.
Author Keywords

Similar Articles

Id	Similarity	Authors	Title	Published
1345	0.933	Khan S.M.; Haider S.A.; Unwala I.	A Deep Learning Based Classifier For Crack Detection With Robots In Underground Pipes	HONET 2020 - IEEE 17th International Conference on Smart Communities: Improving Quality of Life using ICT, IoT and AI (2020)
17076	0.907	Li X.; Ma J.; Yu Z.; Sun L.; Zhu J.; Lin J.	D-Triple: An Optimized Defect Detection Deep Model For Sewer Pipes	Proceedings - 2023 IEEE International Conference on Smart Internet of Things, SmartIoT 2023 (2023)
44341	0.897	Lu J.; Song W.; Zhang Y.; Yin X.; Zhao S.	Real-Time Defect Detection In Underground Sewage Pipelines Using An Improved Yolov5 Model	Automation in Construction, 173 (2025)
26238	0.874	Kumar P.; Purohit G.; Tanwar P.K.; Kota S.R.	Feasibility Analysis Of Convolution Neural Network Models For Classification Of Concrete Cracks In Smart City Structures	Multimedia Tools and Applications, 82, 25 (2023)
61491	0.865	Rayhana R.; Jiao Y.; Liu Z.; Wu A.; Kong X.	Water Pipe Valve Detection By Using Deep Neural Networks	Proceedings of SPIE - The International Society for Optical Engineering, 11382 (2020)
28235	0.862	Xie R.; Chen M.; Tao M.; Ding K.; Chen H.	Gradient And Self-Attention Enabled Convolutional Neural Network For Crack Detection In Smart Cities	Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS (2023)
1383	0.861	Reis H.C.; Turk V.; Kaya Yildiz C.M.; Bozkurt M.F.; Karagoz S.N.; Ustuner M.	A Deep Neural Network Combined With A Two-Stage Ensemble Model For Detecting Cracks In Concrete Structures	Frontiers of Structural and Civil Engineering (2025)
26074	0.853	Wang N.; Chen Y.; Li W.; Zhang L.; Tian J.	Fad-Net: Automated Framework For Steel Surface Defect Detection In Urban Infrastructure Health Monitoring	Big Data and Cognitive Computing, 9, 6 (2025)
61118	0.853	Liu Y.; Zhang X.; Li Y.; Liang G.; Jiang Y.; Qiu L.; Tang H.; Xie F.; Yao W.; Dai Y.; Qiao Y.; Wang Y.	Videopipe 2022 Challenge: Real-World Video Understanding For Urban Pipe Inspection	Proceedings - International Conference on Pattern Recognition, 2022-August (2022)
44423	0.852	Saleem F.; Ahmad Z.; Kim J.-M.	Real-Time Pipeline Leak Detection: A Hybrid Deep Learning Approach Using Acoustic Emission Signals	Applied Sciences (Switzerland), 15, 1 (2025)