Real-Time Detection of Small Liquid Drip in Pipeline in Complex Industrial Scenes Based on Machine Vision
Source abstract
Abstract
Pipeline leakage can lead to catastrophic consequences, and traditional sensor-based detection methods often struggle to identify changes caused by slow or minor leaks. This paper proposes a real-time machine vision-based method for detecting liquid leakage in pipelines, suitable for complex industrial scenarios. By extracting droplet foreground regions and constructing a detection model based on the contour and motion features of droplets, the proposed method effectively filters out interference from lighting variations, equipment vibrations, and personnel movement in industrial environments, while accurately identifying the vertical motion characteristics of dripping liquids. An experimental platform was established to validate the effectiveness of the proposed approach. The results demonstrate that the proposed method achieves a detection rate of 98.04%, a false alarm rate of 5.26%, and a processing speed of 90.71 fps. Comparative experiments show that this method significantly outperforms traditional approaches, such as the dense optical flow method, which yields a higher false alarm rate and a processing speed of only 2.2 fps under the same test conditions. These findings confirm that our approach offers a more accurate and efficient solution for real-time pipeline liquid leakage detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Water Systems and Optimization · Fire Detection and Safety Systems · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu 610059, China
References (32)
Show source-provided references
1. Pipeline Leak Detection System for Oil and Gas Flowlines10.1115/1.2836545 ↗
2. Overview of Pipeline Leakage Detection Sensors and Applications
3. Improved Shock Tube Method for Dynamic Calibration of the Sensitivity Characteristic of Pizoresistive Pressure Sensors10.1016/j.measurement.2022.111271 ↗
4. A Novel Location Algorithm for Pipeline Leakage Based on the Attenuation of Negative Pressure Wave10.1016/j.psep.2019.01.010 ↗
5. Song, P., Ma, Z., Ma, J., Yang, L., Wei, J., Zhao, Y., Zhang, M., Yang, F., and Wang, X. (2020). Recent Progress of Miniature MEMS Pressure Sensors. Micromachines, 11.10.3390/mi11010056 ↗
6. Rathod, V.T. (2019). A Review of Electric Impedance Matching Techniques for Piezoelectric Sensors, Actuators and Transducers. Electronics, 8.10.3390/electronics8020169 ↗
7. Lee, M.-K., Han, S.-H., Park, K.-H., Park, J.-J., Kim, W.-W., Hwang, W.-J., and Lee, G.-J. (2019). Design Optimization of Bulk Piezoelectric Acceleration Sensor for Enhanced Performance. Sensors, 19.10.3390/s19153360 ↗
8. Novel Leakage Detection by Ensemble CNN-SVM and Graph-Based Localization in Water Distribution Systems10.1109/TIE.2017.2764861 ↗
9. Pipeline Leak Detection Technology Based on Distributed Optical Fiber Acoustic Sensing System10.1109/ACCESS.2020.2973229 ↗
10. Principles and Applications of Optical Fiber Distributed Acoustic Sensors
11. Stajanca, P., Chruscicki, S., Homann, T., Seifert, S., Schmidt, D., and Habib, A. (2018). Detection of Leak-Induced Pipeline Vibrations Using Fiber: Optic Distributed Acoustic Sensing. Sensors, 18.10.3390/s18092841 ↗
12. Klein, W.R. (February, January 31). Acoustic Leak Detection. Proceedings of the 16th Annual Energy-Sources Technology Conference and Exhibition, Houston, TX, USA.
13. A Review on Different Pipeline Fault Detection Methods10.1016/j.jlp.2016.03.010 ↗
14. Designing a Cost-Effective and Reliable Pipeline Leak-Detection System
15. Overview of Long Oil and Gas Pipeline Leak Detection Technology
16. Integrated-Signal-Based Leak Location Method for Liquid Pipelines10.1016/j.jlp.2014.10.001 ↗
17. Wang, B., Chen, M., Guan, C., Xia, Z., Gao, Y., and Dong, L. (2025, January 20–21). Oil Leak Detection Method Based on Improved YOLOv7. Proceedings of the IEEE 2nd International Conference on Energy and Electrical Engineering, Nanchang, China.10.1109/EEE64897.2025.11162832 ↗
18. Zhang, J., Lan, X., Wang, S., and Liu, W. (2024, January 20–22). EPA-YOLO: A Lightweight Pipeline Leak Detection Algorithm Based on Improved YOLOv7. Proceedings of the 5th International Conference on Computers and Artificial Intelligence Technology, Hangzhou, China.10.1109/CAIT64506.2024.10963109 ↗
19. Li, Z., Kong, S., Tang, P., Hu, J., Chen, J., and Wang, Q. (2023, January 27–29). A Leak Detection Method for Heat Network pipes Based on YOLOv5 and Automatic Region Growing. Proceedings of the 8th International Conference on Image, Vision and Computing, Dalian, China.10.1109/ICIVC58118.2023.10269876 ↗
20. Rong, S., Hamdan, E., Khaleghi, H., Karatas, A., and Cetin, A.E. (2025, January 25–28). Air Leak Detection Using Sobel-Enhanced YOLO Algorithm from Infrared Images. Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS), London, UK.10.1109/ISCAS56072.2025.11043806 ↗
21. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., and Anadkat, S. (2023). Gpt-4 technical report. arXiv.
22. Jiang, X., Li, J., Deng, H., Liu, Y., Gao, B.-B., Zhou, Y., Li, J., Wang, C., and Zheng, F. (2024). MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection. arXiv.
23. Wei, S., Jiang, J., and Xu, X. (2025, January 11–15). UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection. Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), Nashville, TN, USA. Available online: https://ieeexplore.ieee.org/document/11094947.10.1109/CVPR52734.2025.00934 ↗
24. Shao, Y., He, H., Li, S., Chen, S., Long, X., Zeng, F., Fan, Y., Zhang, M., Yan, Z., and Ma, A. (2025, January 27–31). Eventvad: Training-free event-aware video anomaly detection. Proceedings of the ACM International Conference on Multimedia, Dublin, Ireland.10.1145/3746027.3754500 ↗
25. Zhou, Q., Pang, G., Tian, Y., He, S., and Chen, J. (2023). Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection. arXiv.
26. (2025). Qwen3-VL Technical Report. arXiv.
27. Leakage Identification Model of Digital Twin Pipeline Based on AOA-SVM
28. An Efficient Data-Driven Leak Detection Strategy by Enhancing a Convolutional Neural Network Approach Using a Gaussian Process Regressor10.1007/s11269-025-04403-3 ↗
29. Cherifi, D., Mekroud, S., and Boudaoud, A. (2025). Deep Learning-Based Segmentation for Oil Pipeline Leak Detection Using Quadcopter Drones. Proceedings of International Conference on Artificial Intelligence in Renewable Energetic Systems; Lecture Notes in Networks and Systems, Springer.10.1007/978-3-031-80301-7_37 ↗
30. Li, Y., Liu, Y., Wan, Q., Bi, L., and Yin, X. (2022). Implementation of Underwater Vehicle Pipeline Inspection Based on Machine Vision. Intelligent Networked Things; Communications in Computer and Information Science, Springer.10.1007/978-981-19-8915-5_2 ↗
31. Machine vision for natural gas methane emissions detection using an infra-red camera10.1016/j.apenergy.2019.113998 ↗
32. Research Progress on Optical-Flow-Based Video Vibration Measurement Technology