Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 2, 2026Applied SciencesOpen Access

Integrated UAV Path Planning and Attention-Enhanced Instance Segmentation for Automated Infrastructure Surface Defect Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

YXYuchi XupanYLYu LingHLHua Liu

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved surface defect detection in infrastructures, suggesting a boost in inspection efficiency.

Key Points

  • The study aims to develop a framework for automated detection of surface defects in infrastructure using UAVs and advanced image processing.
  • Utilized 3D model-based adaptive path planning for UAVs
  • Developed an improved instance segmentation model, YOLOv8-seg-ECAC2f-all
  • Conducted a proof-of-concept field study on a concrete viaduct section.
  • Achieved a mean average precision of 91.8% for bounding box detection and 61.7% for instance segmentation
  • Detected all eight ground-truth surface defects during validation
  • Improved detection accuracy for minor spalling cases over manual inspection.

Cite This Study

Xupan et al. (2026) studied this question.

synapsesocial.com/papers/6a6eeae61b0468a7eeab38f4https://doi.org/10.3390/app16157616
View Full Paper
Ask AI
Bookmark
Share