Structural crack intelligence based on lightweight DeepLabv3+identification research
CHEN Zhou
WEN Jiahao
LU Hanwen
DU Heping
Abstract：In order to solve the problems of weak generalization ability and large storage resource demand of existing bridge crack semantic segmentation models,an improved DeepLabv3+model was proposed,which replaced the feature extraction network with the lightweight network MobileNetv2,and combined with the Swish activation function and transfer learning strategy.In order to verify the effectiveness of the improved model,a bridge crack dataset was constructed by using different types of bridge crack images under complex background interference,and the cracks of the improved DeepLabv3+model,DeepLabv3+model,Segnet model and Unet model were trained for crack recognition,and the recognition effects of the four models were compared and analyzed from the aspects of segmentation accuracy,average interaction ratio and model size.The analysis results show that the segmentation accuracy of the improved DeepLabv3+model reaches 93.41%,the average interaction ratio reaches 78.51%,and the F1 score reaches 83.60%.The size of the improved model is only 6.64 MB,which is at the same order of magnitude as the size of the Segnet model and significantly smaller than that of the DeepLabv3+and Unet models.
Keywords：DeepLabv3+MobileNetv2bridge crackstransfer learningsemantic segmentation
Publication Date：2025-11-30
Online Publishing Date：2025-12-12(First online date of this platform, not the publication date of the document)
Pages：7( 45-51 )