期刊
AUTOMATION IN CONSTRUCTION
卷 146, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.autcon.2022.104698
关键词
Pavement crack assessment; Ground penetrating radar; Object detection; YOLOv3; Multiscale feature fusion
This study proposes a YOLOv3 model with four-scale detection layers (FDL) to detect cracks in GPR images. Results show that the YOLOv3-FDL model achieves higher F1 score and mAP on the GPR dataset, indicating improved detection performance compared to the YOLOv3 model.
Pavement crack detection is critical for transportation infrastructure assessment using ground penetrating radar (GPR). This paper describes a YOLOv3 model with four-scale detection layers (FDL) to detect combined B-scan and C-scan GPR images subject to poor detection effects and a high missed detection rate of small crack feature sizes. Multiscale fusion structures, efficient intersection over union (EIoU) loss function, K-means++ clustering, and hyperparameter optimization were used in this proposed model to further improve detection performance. Results indicated that the F1 score and mAP of the YOLOv3-FDL model reached 88.1% and 87.8% and had an 8.8% and 7.5% improvement on the GPR dataset of concealed cracks, respectively, compared with the YOLOv3 model. This illustrated that this model solved the problem of missed crack detection to some extent. Future studies can take these results further, especially the three-dimensional feature analysis of pavement cracks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据