Lightweight Sewer Pipe Crack Detection Method Based on Amphibious Robot and Improved YOLOv8n

被引:0
作者
Lv, Zhenming [1 ]
Dong, Shaojiang [1 ]
He, Jingyao [2 ]
Hu, Bo [3 ]
Liu, Qingyi [3 ]
Wang, Honghang [4 ]
机构
[1] Chongqing Jiaotong Univ, Sch Mechatron & Vehicle Engn, Chongqing 400074, Peoples R China
[2] Chongqing Jiaotong Univ, Engn Res Ctr Diag Technol Hydroconstruct, Chongqing 400074, Peoples R China
[3] Chongqing Inst Surveying & Mapping Sci & Technol, Chongqing 401120, Peoples R China
[4] Shanghai Dianji Univ, Sch Elect, Shanghai 201306, Peoples R China
关键词
sewage pipe robot; lightweight; YOLOv8n; RGCSPELAN; Detect_LADH; LSKA; safe maintenance;
D O I
10.3390/s24186112
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Aiming at the problem of difficult crack detection in underground urban sewage pipelines, a lightweight sewage pipeline crack detection method based on sewage pipeline robots and improved YOLOv8n is proposed. The method uses pipeline robots as the equipment carrier to move rapidly and collect high-definition data of apparent diseases in sewage pipelines with both water and sludge media. The lightweight RGCSPELAN module is introduced to reduce the number of parameters while ensuring the detection performance. First, we replaced the lightweight detection head Detect_LADH to reduce the number of parameters and improve the feature extraction of modeled cracks. Finally, we added the LSKA module to the SPPF module to improve the robustness of YOLOv8n. Compared with YOLOv5n, YOLOv6n, YOLOv8n, RT-DETRr18, YOLOv9t, and YOLOv10n, the improved YOLOv8n has a smaller number of parameters of only 1.6 M. The FPS index reaches 261, which is good for real-time detection, and at the same time, the model also has a good detection accuracy. The validation of sewage pipe crack detection through real scenarios proves the feasibility of the proposed method, which has good results in targeting both small and long cracks. It shows potential in improving the safety maintenance, detection efficiency, and cost-effectiveness of urban sewage pipes.
引用
收藏
页数:19
相关论文
共 48 条
  • [1] Urban Sanitation in al-Andalus: The Case of Qurtuba (Tenth to Thirteenth Century)
    Blanco-Guzman, Rafael
    Atenciano-Crespillo, Jesus
    [J]. AL-MASAQ-JOURNAL OF THE MEDIEVAL MEDITERRANEAN, 2025, 37 (01): : 1 - 23
  • [2] Grad-CAM plus plus : Generalized Gradient-based Visual Explanations for Deep Convolutional Networks
    Chattopadhay, Aditya
    Sarkar, Anirban
    Howlader, Prantik
    Balasubramanian, Vineeth N.
    [J]. 2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, : 839 - 847
  • [3] Evaluation of the Effectiveness of Five Odor Reducing Agents for Sewer System Odors Using an On-Line Total Reduced Sulfur Analyzer
    Choi, Il
    Lee, Hyunjoo
    Shin, Joungdu
    Kim, Hyunook
    [J]. SENSORS, 2012, 12 (12) : 16892 - 16906
  • [4] Xception: Deep Learning with Depthwise Separable Convolutions
    Chollet, Francois
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1800 - 1807
  • [5] DefectTR: End-to-end defect detection for sewage networks using a transformer
    Dang, L. Minh
    Wang, Hanxiang
    Li, Yanfen
    Nguyen, Tan N.
    Moon, Hyeonjoon
    [J]. CONSTRUCTION AND BUILDING MATERIALS, 2022, 325
  • [6] Sewer Inlet Localization in UAV Image Clouds: Improving Performance with Multiview Detection
    de Vitry, Matthew Moy
    Schindler, Konrad
    Rieckermann, Jorg
    Leitao, Joao P.
    [J]. REMOTE SENSING, 2018, 10 (05)
  • [7] Exploring transitions of sewer wastewater infrastructure towards decentralisation using the modular model TURN-Sewers
    Duque, Natalia
    Scholten, Lisa
    Maurer, Max
    [J]. WATER RESEARCH, 2024, 257
  • [8] A robust method for approximate visual robot localization in feature-sparse sewer pipes
    Edwards, S.
    Zhang, R.
    Worley, R.
    Mihaylova, L.
    Aitken, J.
    Anderson, S. R.
    [J]. FRONTIERS IN ROBOTICS AND AI, 2023, 10
  • [9] Detection and classification of pipe defects based on pipe-extended feature pyramid network
    Guo, Wenhao
    Zhang, Xing
    Zhang, Dejin
    Chen, Zhipeng
    Zhou, Baoding
    Huang, Dingfa
    Li, Qingquan
    [J]. AUTOMATION IN CONSTRUCTION, 2022, 141
  • [10] Assessment of Health Risk and Detailed Evaluation of Causative Factors Associated with Use of Contaminated Groundwater in the Remote Atolls
    Hajare, Rajashree
    Labhasetwar, Pawan
    Nagarnaik, Pranav
    [J]. WATER AIR AND SOIL POLLUTION, 2021, 232 (05)