Article Details

Abstract

As a key protective component of the urban underground pipe network system, the safety status of manhole covers directly affects the operation and maintenance efficiency and public safety of municipal facilities. To address the inefficiency and high false alarm rate of traditional methods for detecting hidden dangers in manhole covers, this paper proposes an intelligent detection method based on improved YOLOv5. By constructing a multi-scale feature fusion mechanism, this paper combines the 5-fold cross-validation method to train the model of the labeled dataset, and realizes the accurate identification of typical safety hazards such as breakage, displacement, loss, and so on. The experimental results show that the mean Average Precision (mAP) of the improved model on the self-constructed manhole cover dataset is 95.2%. Compared with the YOLOv4 model, the accuracy and detection speed are improved. By optimizing the Feature Pyramid Network structure and loss function, the algorithm effectively enhances the target representation ability in complex road scenarios, providing reliable technical support for intelligent operation and maintenance of urban infrastructure.

Keywords

hidden danger of manhole cover; YOLOv5; object detection; activation function

References

1. [1] Kong Tianyu, wear a laser Improving the detection of pavement manhole cover diseases in YOLOv5 [J]. Remote Sensing Information, 2023, 38 (3): 40-46
2. [2] Chen Xinrui, Zhou Yang, Zhao Yitao, etc Mobile end bolt missing detection method based on improved YOLOv5 [J]. Modern Manufacturing Engineering, 2022 (11): 108-114+143
3. [3] Zhu Jiuniu, Li Liming, Chai Xiaodong, etc Research on the bolt positioning method of subway vehicle axle box cover based on improved YOLOv5 algorithm [J]. Intelligent Computer and Application, 2023, 13 (10): 29-34
4. [4] Wang Wensheng, Nian Chengxu, Zhang Chao, etc Design of Automatic Garbage Classification Bin for Non Residential Areas Based on YOLOv5 Model [J]. Environmental Engineering, 2022, 40 (3): 159-165
5. [5] Lei Junhua Design and Implementation of Garbage Detection System in Complex Background Based on Improved YOLOv5s [D]. Wuhan: Central South University of Economics and Law, 2023
6. [6] Wu Songying, Liu Linya, Jiang Jiaming, etc Improved YOLOv5s detection algorithm for railway fasteners in complex backgrounds [J]. China Railway Science, 2023, 44 (3): 53-63
7. [7] Xiang Rongrong, Li Bo, Zhao Qiao Mask wearing detection algorithm based on improved YOLOv5s [J]. Foreign Electronic Measurement Technology, 2022, 41 (7): 39-44
8. [8] Hui Kanghua, Liu Chang Small scale face detection method based on YOLO5Face redistribution [J]. Computer Simulation, 2024, 41 (3): 206-213
9. [9] Lin Gang, Wei Xin, Liu Chunsheng, etc A surface defect detection method for daily-use ceramics based on regional division and YOLO5 CN202211193767.1 [P].2023-01-06.
10. [10] Ni Weiguo, Huang Xiaorong, Li Xin, etc Research on the Intelligent Fire Inspection System for Unmanned Aerial Vehicles Based on YOLO5 [J]. China Broadband, 2023, 19 (3): 193-195
11. [11] Liu Yinlong, Wang Jie, Cao Ang, etc Visual defect detection method for aluminum profiles based on YOLOv5s [J]. Manufacturing Automation, 2024, 46 (1): 169-173

Funding

Shaanxi Province College Students Innovation and Entrepreneurship Plan Project (S202412715035)

About the authors

Huang Jian (1973-), male, Han ethnicity, from Fuping, Shaanxi Province, associate professor, master's student, research direction: embedded development technology.