EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Defect Detection and 3D Reconstruction of Complex Urban Underground Pipeline Scenes for Sewer Robots

Ruihao Liu iD, Zhongxi Shao iD, Qiang Sun, Zhenzhong Yu

Sensors · 26.11.2024 · 24 (23) · 7557

DOI: 10.3390/s24237557 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.11.2024. Verfasst von Ruihao Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150001, China. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Major Science and Technology Projects of Anhui Province, Major Science and Technology Projects of Anhui Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting defects in complex urban sewer scenes is crucial for urban underground structure health monitoring. However, most image-based sewer defect detection models are complex, have high resource consumption, and fail to provide detailed damage information. To increase defect detection efficiency, visualize pipelines, and enable deployment on edge devices, this paper proposes a computer vision-based robotic defect detection framework for sewers. The framework encompasses positioning, defect detection, model deployment, 3D reconstruction, and the measurement of realistic pipelines. A lightweight Sewer-YOLO-Slim model is introduced, which reconstructs the YOLOv7-tiny network by adjusting its backbone, neck, and head. Channel pruning is applied to further reduce the model’s complexity. Additionally, a multiview reconstruction technique is employed to build a 3D model of the pipeline from images captured by the sewer robot, allowing for accurate measurements. The Sewer-YOLO-Slim model achieves reductions of 60.2%, 60.0%, and 65.9% in model size, parameters, and floating-point operations (FLOPs), respectively, while improving the mean average precision (mAP) by 1.5%, reaching 93.5%. Notably, the pruned model is only 4.9 MB in size. Comprehensive comparisons and analyses are conducted with 12 mainstream detection algorithms to validate the superiority of the proposed model. The model is deployed on edge devices with the aid of TensorRT for acceleration, and the detection speed reaches 15.3 ms per image. For a real section of the pipeline, the maximum measurement error of the 3D reconstruction model is 0.57 m. These results indicate that the proposed sewer inspection framework is effective, with the detection model exhibiting advanced performance in terms of accuracy, low computational demand, and real-time capability. The 3D modeling approach offers valuable insights for underground pipeline data visualization and defect measurement.

Schlagwörter

Stichwörter der Autor:innen

3D reconstructionYOLO networkdefect detectionedge deploymentlightweighturban pipeline

Autor:innen und Institutionen

  • School of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150001, China.
  • Hefei Intelligent Robot Institute, Hefei 230601, China.

ORCID-Profile: Ruihao Liu, Zhongxi Shao

Förderung

  • the Major Science and Technology Projects of Anhui Province
  • Major Science and Technology Projects of Anhui Province

Zitieren

APA

Liu, R., Shao, Z., Sun, Q., & Yu, Z. (2024). Defect Detection and 3D Reconstruction of Complex Urban Underground Pipeline Scenes for Sewer Robots. Sensors, 24(23), 7557. https://doi.org/10.3390/s24237557

Vancouver

Liu R, Shao Z, Sun Q, Yu Z. Defect Detection and 3D Reconstruction of Complex Urban Underground Pipeline Scenes for Sewer Robots. Sensors. 2024;24(23):7557. doi:10.3390/s24237557

BibTeX
@article{Liu2024,
  author = {Liu, Ruihao and Shao, Zhongxi and Sun, Qiang and Yu, Zhenzhong},
  title = {Defect Detection and 3D Reconstruction of Complex Urban Underground Pipeline Scenes for Sewer Robots},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {23},
  pages = {7557},
  doi = {10.3390/s24237557}
}
Kostenlos starten →