YOLO vs. diffusion networks for underground pipe detection: a case study using ground penetrating radar data

Abstract

The accurate detection and mapping of underground pipelines are critical for urban planning and infrastructure resilience. This process is critical to prevent catastrophic failures, minimize service disruptions, and maintain the structural integrity of public works projects. Ground Penetrating Radar (GPR) is a prominent technology for the automated detection and precise localization of subsurface utilities. However, the current dependence on manual data interpretation is a major bottleneck, often resulting in high temporal and operational costs. Consequently, this research addresses these limitations by presenting a performance analysis of two distinct deep learning architectures–YOLO (You Only Look Once) and Diffusion-based neural networks–for automated underground pipe detection. Utilizing a specific dataset of GPR scans, the models were evaluated using a robust five-fold cross-validation framework to assess mean Average Precision at 50% Intersection over Union (mAP50) and inference latency. The experimental results demonstrate that YOLO-based architectures provide a superior balance between detection precision and real-time processing efficiency. While five-fold cross-validation established a mean mAP50 of approximately 80% for the YOLO models, the YOLOv12n architecture exhibited superior performance on the independent test set, achieving an mAP50 of 94%. In contrast, DiffusionDet models were characterized by lower precision and significantly higher latency. While this study focuses on a single-site case study, the findings establish a foundational baseline for the selection of deep learning architectures and provide a framework for future research into the adaptation of these models across varying geological conditions.

A Fast Denoising Dataset-Generation Method for Ground Penetrating Radar Based on a Transformer Network Constrained by an Underground Clutter Physical Model
Yuxuan Wu, Xiaole Ma, Feng Shen +1
Sensors (Basel, Switzerland)1 Oct 2026Peer-reviewedCC BYFull textEurope PMC
Machine learning assisted seismic assessment of rock crack propagation and ground instability around underground passageways
Lijie Long, Yan Liu, A. Fazli Shahgoli +2
Scientific Reports7 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textCrossref
Non-destructive evaluation of thermal conductivity of wood and insulation materials using permittivity measurements with ground penetrating radar
Jinxia Hu, Ryad Bouzouidja, Tingting Vogt Wu +1
Energy and Buildings16 Sep 2026Peer-reviewedCC BY5 citedGeneral physicsHAL
Robust Range-Doppler Acoustic Feature Fusion for Unauthorised Personnel Crossing Detection on Underground Belt Conveyors
Yuqing Yin, Baoxuan Xu, Xu Yang +1
Sensors (Basel, Switzerland)1 Oct 2026Peer-reviewedCC BYFull textEurope PMC
An Underground Energized Cable Detection Method Based on the Fusion of Real-World Simulation and Characteristic Time Sequence
Sun Tiancheng, Tan Yongqiang, Yang Xi +3
Measurement Science Review26 Oct 2026Peer-reviewedCC BY-NC-NDFull textGeneral mathematicsDOAJ

Cite

BibTeX RIS

BibTeX

@article{senousy2026yolo,
  title = {{YOLO vs. diffusion networks for underground pipe detection: a case study using ground penetrating radar data}},
  author = {Doaa N. Senousy and Omar M. Saad and Shereen M. Ebrahim and Abbas Mohamed Abbas and Amr M. Gody},
  journal = {Scientific Reports},
  year = {2026},
  month = nov,
  doi = {10.1038/s41598-026-73688-0},
  url = {https://www.nature.com/articles/s41598-026-73688-0},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - YOLO vs. diffusion networks for underground pipe detection: a case study using ground penetrating radar data
AU  - Doaa N. Senousy
AU  - Omar M. Saad
AU  - Shereen M. Ebrahim
AU  - Abbas Mohamed Abbas
AU  - Amr M. Gody
PY  - 2026
DA  - 2026/11/04
JO  - Scientific Reports
DO  - 10.1038/s41598-026-73688-0
UR  - https://www.nature.com/articles/s41598-026-73688-0
AB  - The accurate detection and mapping of underground pipelines are critical for urban planning and infrastructure resilience. This process is critical to prevent catastrophic failures, minimize service disruptions, and maintain the structural integrity of public works projects. Ground Penetrating Radar (GPR) is a prominent technology for the automated detection and precise localization of subsurface utilities. However, the current dependence on manual data interpretation is a major bottleneck, often resulting in high temporal and operational costs. Consequently, this research addresses these limitations by presenting a performance analysis of two distinct deep learning architectures–YOLO (You Only Look Once) and Diffusion-based neural networks–for automated underground pipe detection. Utilizing a specific dataset of GPR scans, the models were evaluated using a robust five-fold cross-validation framework to assess mean Average Precision at 50% Intersection over Union (mAP50) and inference latency. The experimental results demonstrate that YOLO-based architectures provide a superior balance between detection precision and real-time processing efficiency. While five-fold cross-validation established a mean mAP50 of approximately 80% for the YOLO models, the YOLOv12n architecture exhibited superior performance on the independent test set, achieving an mAP50 of 94%. In contrast, DiffusionDet models were characterized by lower precision and significantly higher latency. While this study focuses on a single-site case study, the findings establish a foundational baseline for the selection of deep learning architectures and provide a framework for future research into the adaptation of these models across varying geological conditions.
SN  - 2045-2322
ER  -

Abstract

Related

Cite