Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 11, 2026Journal of Computing in Civil Engineering

Addressing Data Scarcity in GPR Road Defect Detection: A Novel Framework Combining Stable Diffusion and Efficient GCP-YOLO

View Full Paper
Ask AI
Bookmark
Share

Authors

MCMinxing CuiTongji UniversityYDYanliang DuShijiazhuang Tiedao UniversityDWDifei WuTongji University

Discussion

Loading...

Member takes

Overview

Randomized trial explores enhanced GPR defect detection, indicating better precision with synthetic data augmentations.

Key Points

  • This research aims to improve the detection of road subsurface defects using deep learning techniques, specifically by addressing data scarcity.
  • Integrated Stable Diffusion for data augmentation with GPR B-scans.
  • Constructed mixed data sets of real and synthetic data for model training.
  • Tailored and tested multiple YOLOv8 models for precision and efficiency.
  • Achieved improvement in mean average precision ranging from 5.5% to 18.2%.
  • GCP (2)-YOLO model had the highest detection precision but with greater training time costs.
  • GC-YOLO and GCP (6)-YOLO offered better trade-offs between precision and training time.

Cite This Study

Cui et al. (2026) studied this question.

synapsesocial.com/papers/6a2a50e080c8f91e7f39d44ehttps://doi.org/10.1061/jccee5.cpeng-7693
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1GhostNet: More Features From Cheap Operations2020 · 4,778 citations
  2. 2Application of an Improved YOLOv5 Algorithm in Real-Time Detection of Foreign Objects by Ground Penetrating Radar2022 · 77 citations
  3. 3Detection and Discrimination of Land Mines in Ground-Penetrating Radar Based on Edge Histogram Descriptors and a Possibilistic $K$-Nearest Neighbor Classifier2008 · 212 citations