International Journal of Advances in Engineering & Scientific Research
Print ISSN : 2349 –4824
Online ISSN : 2349 –3607
Frequency : Continuous
Current Issue : Volume 12 , Issue 1
2025
Mr.K.Karthick, Ragavi.K.G, Riyasri.K, Yogeswari.M
Mr.K.Karthick, Ragavi.K.G, Riyasri.K, Yogeswari.M, Department of Computer Science and Engineering, Kongunadu College of Engineering and Technology, Tamilnadu, India
DOI : https://doi.org/10.5281/zenodo.14922204 Page No : 45-56
Published Online : 2025-02-25
Download Full Article : PDF Check for Updates
Drainage pipeline maintenance is crucial for urban infrastructure, as undetected defects can lead to severe environmental and structural issues. Traditional inspection methods rely on manual analysis, which is time-consuming, costly, and prone to errors. To address these challenges, this research proposes an Intelligent Drainage Pipeline Defect Detection System utilizing an advanced YOLOv8-DeepSORT model. The YOLOv8 (You Only Look Once) model, known for its high accuracy and real-time object detection capabilities, is employed to detect various pipeline defects such as cracks, corrosion, leaks, and blockages. To enhance tracking efficiency, the Deep SORT (Simple Online and Real time Tracker) algorithm is integrated, enabling seamless object tracking across multiple frames in video inspections. The proposed system processes real-time CCTV footage from pipeline inspections, automatically identifying and tracking defects with high precision. Experimental results demonstrate superior detection accuracy, improved tracking stability, and reduced false positives compared to traditional methods. The system effectively streamlines defect monitoring, allowing for automated, efficient, and cost-effective drainage infrastructure maintenance. This intelligent approach minimizes human intervention, enhances predictive maintenance, and ensures the long-term sustainability of urban drainage networks. Future enhancements may include integrating AI-driven anomaly prediction and IoT-based real-time monitoring systems.
Keywords: YOLOv8, Deep SORT, pipeline defect detection, drainage inspection, real-time monitoring and automated maintenance.
