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...

Полное описание

Библиографические подробности

Главные авторы:	Zichen Zhang, Chengjun Guo
Формат:	Artigo
Язык:	Inglês
Опубликовано:	MDPI AG 2026-05-01
Серии:	Buildings
Предметы:	YOLOv11 object detection dual attention mechanism geometry-constrained attention residual channel attention
Online-ссылка:	https://www.mdpi.com/2075-5309/16/11/2105
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!