Incorporating Structural Prior Knowledge into YOLO for Robust Infrastructure Damage Detection

Vision-based structural defect detection methods based on YOLOv11 have achieved promising performance in recent years; however, their robustness in real engineering environments remains limited due to illumination variation, shadow occlusion, surface contamination, and complex background textures. E...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Zichen Zhang, Chengjun Guo
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2026-05-01
Schriftenreihe:	Buildings
Schlagworte:	YOLOv11 object detection dual attention mechanism geometry-constrained attention residual channel attention
Online-Zugang:	https://www.mdpi.com/2075-5309/16/11/2105
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!