With the increasing frequency of extreme weather events, road waterlogging has posed a serious threat to urban traffic safety and residents’ daily travel. Traditional detection methods, such as manual inspection and sensor deployment, have limitations including high cost, limited coverage, and insufficient real-time performance. In recent years, deep learning-based object detection methods have shown advantages in complex environments. This study proposes an automatic road waterlogging detection method based on the YOLOv8n model. By training and testing on a self-constructed dataset, the model achieved 92.1% [email protected], 91.4% Precision, and 80.3% Recall. The results indicate that YOLOv8n can achieve high detection accuracy and good real-time performance in waterlogging detection, providing a feasible technical solution for smart monitoring of urban waterlogging.

Yuanhao Ding, Yushen Liu. Road Waterlogging Detection Based on YOLOv8n. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 9: 54-59. https://doi.org/10.25236/AJCIS.2025.080908.

[1] Hong S, Shen J, Yang H, et al.Enhancing flexibility and efficiency for urban waterlogging response scenarios simulation: an open-ended approach involving user participation[J].International Journal of Digital Earth, 2025,18(1).

[2] Hu X,Gu F .Urban waterlogging early warning model based on particle swarm optimization and deep neural network: a case study of Hefei old city[J].Urban Water Journal,2025,22(7):738-750.

[3] Sheng Z,Chen F,Liu Q, et al.Real-Time Waterlogging Monitoring on Urban Roads Using Edge Computing[J].Water Resources Management,2025,(prepublish):1-15.

[4] Wu P,Wang T,Wang Z, et al.Impact of Drainage Network Structure on Urban Inundation Within a Coupled Hydrodynamic Model[J].Water,2025,17(7):990-990.

[5] Sam A T, Apurba P, Sara A, et al. Rational design of a solvatochromic coumarin aldehyde for the development of an effective water and humidity sensor. Dyes and Pigments, 2023, 216.

[6] Ling Y,Wonjun C .Analysis of material and craft aesthetics characteristics of arts and crafts works based on computer vision[J].Journal of Experimental Nanoscience,2023,18(1).

[7] Liu J,Xie Y,Zhang Y, et al.Vehicle Flow Detection and Tracking Based on an Improved YOLOv8n and ByteTrack Framework[J].World Electric Vehicle Journal,2024,16(1):13.

[8] Zhu K,Lyu H,Qin Y .Enhanced detection of small and occluded road vehicle targets using improved YOLOv5[J].Signal, Image and Video Processing,2024,19(1):168.

[9] Rathod V,Rana D,Mehta R .Road Crack Detection and Classification Using UAV and Deep Transfer Learning Optimization[J].Journal of the Indian Society of Remote Sensing,2024,53(6):1-17.

[10] Garta Y I,Tai K S,Chen C R .Improved Detection of Multi-Class Bad Traffic Signs Using Ensemble and Test Time Augmentation Based on Yolov5 Models[J].Applied Sciences, 2024, 14(18): 8200-8200.

[11] Tao H,Paul A,Wu Z .Infrared Image Detection and Recognition of Substation Electrical Equipment Based on Improved YOLOv8[J].Applied Sciences,2024,15(1):328.

[12] Liu C,Ma L,Sui X, et al.YOLO-CSM-Based Component Defect and Foreign Object Detection in Overhead Transmission Lines[J].Electronics,2023,13(1).

[13] Zhang Y,Guo R,Li M .Backend-free multi-scale feature fusion network for defect detection in printed circuit board images[J].Journal of Real-Time Image Processing,2025,22(5):187.

[14] Jinlin X,Feng C,Yuqing L, et al.Detection of Farmland Obstacles Based on an Improved YOLOv5s Algorithm by Using CIoU and Anchor Box Scale Clustering[J].Sensors,2022,22(5):1790.

[15] Zhang J,Gao M,Song L, et al.REA-YOLO for small object detection in UAV aerial images[J]. The Journal of Supercomputing,2025,81(14):1332.