Single-Camera Flood Monitoring Using YOLOv5 for Water Level and Turbidity Detection

Gamma Aditya Rahardi; Sherly Apta Maharani; Hasanur Mohammad Firdausi; Satryo Budi Utomo; Dani Hari Tunggal Prasetiyo

doi:10.33019/

Authors

Gamma Aditya Rahardi Department of Electrical Engineering, University of Jember
Sherly Apta Maharani Department of Electrical Engineering, University of Jember
Hasanur Mohammad Firdausi Department of Informatics, KH Bahaudin Mudhary Madura University
Satryo Budi Utomo Department of Electrical Engineering, University of Jember
Dani Hari Tunggal Prasetiyo Department of Mechanical Engineering, University of Jember

DOI:

https://doi.org/10.33019/

Keywords:

Computer Vision, Flood Monitoring, Water Level, Water Turbidity, YOLOv5

Abstract

Floods are one of the most common natural disasters and require efficient early warning systems to mitigate their effects on infrastructure and communities. Conventional flood monitoring systems generally consist of many physical sensors, which may incur higher maintenance cost and reduce the system robustness in a severe river environment. The purpose of this study is to create a single-camera flood monitoring system that is capable of detecting water level and water turbidity in real-time using YOLOv5. An initial dataset containing 1,711 original images was collected and augmented to 4,104 images for model training and evaluation. Four YOLOv5 variants (YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) were trained for 50 and 150 epochs. Experimental results show that all models have high detection performance with precision, recall and mAP values above 0.98. YOLOv5s achieved the best real-time performance with 4.26 FPS and maintained competitive accuracy. Detection failures due to overexposure were observed at high illumination levels and illumination analysis indicated that detection can be reliably performed under lighting conditions below 25,000 lux. The proposed system provides a vision-based alternative for real-time inundation early warning applications.

Downloads

Download data is not yet available.

References

[1] H. Adikari, C. O’Leary, J. Harrington, and C. Lynch, “Computer vision in flash flood forecasting: A narrative review of applications, integration pathways, and future directions,” Environmental Modelling & Software, vol. 198, p. 106910, Mar. 2026, doi: 10.1016/j.envsoft.2026.106910.

[2] W. Almikaeel, A. Šoltész, L. Čubanová, and D. Baroková, “Hydro-informer: a deep learning model for accurate water level and flood predictions,” Natural Hazards, vol. 121, no. 4, pp. 3959–3979, Mar. 2025, doi: 10.1007/s11069-024-06949-8.

[3] S. T. Chowdhury, F. Yasmin, M. M. P. Tanni, M. Rahman, H. Sarwar, and T. T. Tin, “A systematic review of flood prediction (2018–2025): Flood categories, input features, and Machine Learning, Deep Learning and hybrid approaches,” Watershed Ecology and the Environment, vol. 8, pp. 185–207, Jan. 2026, doi: 10.1016/j.wsee.2026.03.002.

[4] L. Shuiquan et al., “Urban flood disaster prevention, control, and rescue using edge computing and the resilience concept,” Sci. Rep., vol. 16, no. 1, p. 1888, Dec. 2025, doi: 10.1038/s41598-025-31599-6.

[5] V. N. Tran et al., “Designing an inundation monitoring and real-time urban flood forecasting system: a synthetic study,” J. Hydrol. (Amst)., vol. 674, p. 135520, Jul. 2026, doi: 10.1016/j.jhydrol.2026.135520.

[6] W. Weber de Melo, I. Iglesias, and J. Pinho, “Early warning system for floods at estuarine areas: combining artificial intelligence with process-based models,” Natural Hazards, vol. 121, no. 4, pp. 4615–4638, Mar. 2025, doi: 10.1007/s11069-024-06957-8.

[7] B. Liu, Y. Li, M. Ma, and B. Mao, “A Comprehensive Review of Machine Learning Approaches for Flood Depth Estimation,” International Journal of Disaster Risk Science, vol. 16, no. 3, pp. 433–445, Jun. 2025, doi: 10.1007/s13753-025-00639-0.

[8] G. A. Rahardi, W. Muldayani, M. D. A. Wijaya, D. Setiabudi, and H. M. Firdausi, “Early Warning System Design for Flood Disasters Using the IoT-Based Fuzzy Logic Control Method,” in 2022 International Conference on Electrical Engineering, Computer and Information Technology (ICEECIT), IEEE, Nov. 2022, pp. 131–135. doi: 10.1109/ICEECIT55908.2022.10030237.

[9] R. Y. Douss, S. Chaabouni, and A. Benazza-Benyahia, “Water turbidity monitoring application combining IoT and computer vision tools,” in 2023 International Conference on Cyberworlds (CW), IEEE, Oct. 2023, pp. 498–499. doi: 10.1109/CW58918.2023.00085.

[10] A. B. S, A. D. P, K. kumaran T. S, and A. N. S, “Data-Driven Approach for Water Quality Monitoring in Aquaculture using IoT,” in 2025 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI), IEEE, Sep. 2025, pp. 1500–1505. doi: 10.1109/ICoICI65217.2025.11253980.

[11] A. Zuhaer, A. Khandoker, N. Enayet, P. K. P. Partha, and Md. A. Awal, “Sustainable aquaculture: An Iot-integrated system for real-time water quality monitoring featuring advanced do and ammonia sensors,” Aquac. Eng., vol. 112, p. 102620, Jan. 2026, doi: 10.1016/j.aquaeng.2025.102620.

[12] S. Neupane, J. S. Horsburgh, R. Bin Issa, and S. Young, “HydrocamCollect: A robust data acquisition and cloud data transfer workflow for camera-based hydrological monitoring,” Environmental Modelling & Software, vol. 196, p. 106770, Jan. 2026, doi: 10.1016/j.envsoft.2025.106770.

[13] L. Rasheed, A. Sreeram, K. R, S. Latha, T. S. Murugan, and S. Dhanalakshmi, “Intelligent Aquarium Monitoring System Using YOLOv5 and IoT-Based Environmental Sensing,” in 2025 IEEE 22nd India Council International Conference (INDICON), IEEE, Dec. 2025, pp. 1–6. doi: 10.1109/INDICON68490.2025.11393016.

[14] R. Sundarrajan, M. Ramakrishnan, R. S. Dharshini, M. Jeevananthakumar, and M. S, “Smart Algae Cultivation: Real-Time Monitoring and Debris Removal with YOLOv5 and IoT-based Water Quality Sensors,” in 2025 7th International Conference on Intelligent Sustainable Systems (ICISS), IEEE, Mar. 2025, pp. 744–747. doi: 10.1109/ICISS63372.2025.11076514.

[15] B. Andò, S. Castorina, and S. Graziani, “A Vision-Based Solution for Water Level Monitoring in Flash Floods Scenario,” in 2024 IEEE Sensors Applications Symposium (SAS), IEEE, Jul. 2024, pp. 1–6. doi: 10.1109/SAS60918.2024.10636654.

[16] P. Borwarnginn, J. H. Haga, and W. Kusakunniran, “Water Level Detection from CCTV Cameras using a Deep Learning Approach,” in 2020 IEEE REGION 10 CONFERENCE (TENCON), IEEE, Nov. 2020, pp. 1283–1288. doi: 10.1109/TENCON50793.2020.9293865.

[17] L.-C. Kuo and C.-C. Tai, “Robust Image-Based Water-Level Estimation Using Single-Camera Monitoring,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–11, 2022, doi: 10.1109/TIM.2022.3161691.

[18] W.-C. Liu and W.-C. Huang, “Evaluation of deep learning computer vision for water level measurements in rivers,” Heliyon, vol. 10, no. 4, p. e25989, Feb. 2024, doi: 10.1016/j.heliyon.2024.e25989.

[19] M. N. Motlagh, S. Young, K. Chapman, E. Wilcox, and F. Birgand, “Computer vision-based monitoring of stormwater discharge: proof-of-concept for stage measurements,” J. Hydrol. (Amst)., vol. 675, p. 135618, Aug. 2026, doi: 10.1016/j.jhydrol.2026.135618.

[20] A. Shiran, J. Li, Y. Liu, M. Hummel, O. Jenewein, and K. Bezboruah, “Water Level Detection in Adverse Weather Conditions Using Security Cameras,” in SoutheastCon 2024, IEEE, Mar. 2024, pp. 187–193. doi: 10.1109/SoutheastCon52093.2024.10500219.

[21] Ş. Karcı, E. Özceylan Aslan, K. Yıldız, and Ö. Demir, “Deep learning based flood segmentation: evaluating EfficientNet and ResNet for UNet, SegNet and DeepLabV3+,” Natural Hazards, vol. 122, no. 6, p. 263, Mar. 2026, doi: 10.1007/s11069-026-07972-7.

[22] Y. Wang et al., “Urban flood extent segmentation and evaluation from real-world surveillance camera images using deep convolutional neural network,” Environmental Modelling & Software, vol. 173, p. 105939, Feb. 2024, doi: 10.1016/j.envsoft.2023.105939.

[23] P. Zhong, Y. Liu, H. Zheng, and J. Zhao, “Detection of Urban Flood Inundation from Traffic Images Using Deep Learning Methods,” Water Resources Management, vol. 38, no. 1, pp. 287–301, Jan. 2024, doi: 10.1007/s11269-023-03669-9.

[24] M. Kögel and D. Carstensen, “Near real-time change detection tool for photogrammetric flood preparedness,” Environ. Monit. Assess., vol. 197, no. 2, p. 129, Jan. 2025, doi: 10.1007/s10661-024-13597-9.

[25] M. Cai et al., “Lightweight highland barley detection based on improved YOLOv5,” Plant Methods, vol. 21, no. 1, p. 42, Mar. 2025, doi: 10.1186/s13007-025-01353-0.

[26] H. Prince and B. T, “Transformer-enhanced YOLOv5 With cross-convolution for underwater object detection,” Journal on Advances in Signal Processing, vol. 2026, no. 1, p. 51, Apr. 2026, doi: 10.1186/s13634-026-01315-1.

[27] S. Shukri et al., “YOLO-based real-time floating debris counting in urban rivers for flood monitoring and water resource management,” Environ. Monit. Assess., vol. 198, no. 3, p. 232, Feb. 2026, doi: 10.1007/s10661-026-15040-7.