Real-Time Concrete Crack Feature Detection by Segmentation YOLOv11

Abstract

In recent years, structural damage identification has emerged as a pivotal research focus within the field of Structural Health Monitoring (SHM). Currently, in-situ inspections primarily rely on traditional or manual measurement techniques, which demand substantial investments in both human resources and specialized instrumentation. Against this backdrop, the rapid advancement of Deep Learning models has surfaced as a highly promising approach to address these inherent limitations. This study proposes a solution utilizing the YOLOv11 computer vision model to automate the detection and analysis of geometric crack characteristics-including length, width, area, and orientation-in real-time from video or camera input data. Experimental results indicate that the loss function achieved stabilized convergence at the 175th epoch. With a mAP@50 of 80% and a mAP@50-95 of 60%, the model demonstrates robust performance in identifying crack objects, which are typically characterized by complex morphologies and ambiguous boundaries. This method exhibits significant potential for the automation of structural damage inspection and measurement.