Detection of cracks in bridge rubber bearings based on an improved YOLOv8 algorithm
LIANG Dong
HU Yaozong
HUANG Haibin
YU Yang
LIU Yanxing
DONG Jiaohui
Abstract：To address the challenges of complex backgrounds,deep placement and difficulty in recog-nizing and measuring cracks in plate rubber bearings of beam bridges,this study proposes an auto-matic crack detection and parameter calculation method based on dual-stage semantic segmentation using the YOLOv8-ESF framework.First,the EfficientViT backbone is integrated into the back-bone network.Based on this,the Bottleneck structure within the C2f module is reconstructed to form the C2f-Faster-EMA module,which replaces part of the original C2f modules in the YO-LOv8n backbone and incorporates decoupled heads,thereby enhancing the model's ability to cap-ture multi-scale detail features of bearing cracks.Second,the improved YOLOv8n model is em-ployed to segment and extract the entire bearing region.Subsequently,the same model is used to fur-ther segment crack regions within the extracted bearing image.Crack parameters are then obtained by extracting the skeleton centerline and searching for the maximum outer rectangle method.Fi-nally,the model is validated and evaluated from three aspects:network architecture,crack dataset,and segmentation accuracy.Experimental results show that YOLOv8-ESF model achieves over 85%accuracy in terms of mPA,DSC,and IoU for both bearing region and crack recognition.In field tests on real bridges,the maximum deviation between the crack parameters calculated via the dual-stage semantic segmentation method and manual measurements is less than 0.1 mm,meeting practical engineering requirements.
Keywords：bridge engineeringplate rubber bearingaging-induced crackingsemantic segmenta-tionimage processing
Publication Date：2025-08-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：12( 142-153 )