What question did this study set out to answer?

The research aims to improve accuracy in crack segmentation and spatial localization using UAV imagery.

April 17, 2026SymmetryOpen Access

Keyframe-Guided Crack Segmentation and 3D Localization for UAV-Based Monocular Inspection

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates improved crack segmentation and localization in UAV imagery, suggesting enhanced efficiency for inspections.

The research aims to improve accuracy in crack segmentation and spatial localization using UAV imagery.
Implementing ORB-SLAM3 for keyframe selection to reduce data redundancy
Developing an enhanced YOLOv11-seg model incorporating DWRSeg and WIoU loss
Utilizing LSCSBD for efficient batch normalization and detection
Projecting predicted masks onto a 3D surface for localization
Achieved a 7.2% improvement in segmentation mAP@50 compared to baseline
Reduced computational complexity from 10.2 to 9.8 GFLOPs
Cut 3D modeling time by 59.4% using keyframe processing

Tang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark