基于可变形卷积网络和YOLOv8的衬砌裂缝检测模型研究
Research on detection model of lining crack based on deformable convolutional network and YOLOv8
孙己龙 1刘勇 2路鑫 3王志丰 2王亚琼 2侯小龙2
作者信息
- 1. 陕西省交通运输工程质量监测鉴定站,陕西 西安 710075
- 2. 长安大学 公路学院,陕西 西安 710064
- 3. 长安大学 材料科学与工程学院,陕西 西安 710064;西安公路研究院有限公司,陕西 西安 710065
- 折叠
摘要
为解决裂缝性状发育随机度高、标注框分辨率低、分布密集易重叠、目标相对小等因素引起的智能检测精度及效率差等问题,基于改进可变形卷积神经网络对YOLOv8 骨干网络进行融合,提出1 种能够适应隧道复杂场景的裂缝检测模型D-YOLO.模型首先对第3 版可变形卷积网络(DCNv3)的空间聚合权重softmax归一化步骤进行去除以增强网络卷积效率,再利用新DC-Nv4 对骨干网络C2f卷积模块进行融合以提升对网络图像中不同尺度裂缝性状及空间位置变化的细节感知能力,并采用自建裂缝数据集对SSD,Faster-RCNN,YOLOv5 和 YOLOv8 4 种检测模型进行对比验证.研究结果表明:D-YOLO 的 F1 分数为80.82%,mAP@0.5 为86.90%,相较于SSD、Faster-RCNN、YOLOv5 和YOLOv8 都有所提升;D-YOLO的单张图像检测速度为20.36 ms,相较于各种对比模型分别加快37.06%、65.33%、45.22%和 28.39%;同时,D-YOLO对衬砌裂缝图像特征关注范围有所增加.研究结果可为隧道运营期内衬砌安全检测提供新思路.
Abstract
In order to solve the problems of poor intelligent detection accuracy and efficiency caused by the factors such as high randomness of crack characteristic development,low resolution of annotation box,dense distribution and easy overlap,and relatively small target,the YOLOv8 backbone network was fused based on the improved deformable convolutional neural net-work,and a crack detection model D-YOLO that can adapt to complex tunnel scenes was proposed.The normalization step of spatial aggregation weight softmax in the deformable convolutional network v3(DCNv3)was removed to enhance the convolu-tional efficiency of network,and the new DCNv4 was used to fuse the C2f convolution module of backbone network to enhance the detail perception ability of different scale crack characteristics and spatial position change in the network images.The self-built crack dataset was used to compare and verify four detection models including SSD,Faster-RCNN,YOLOv5,and YOLOv8.The results show that the F1 score of D-YOLO is 80.82%,mAP@0.5 is 86.90%,and both of them are improved than those of SSD,Faster-RCNN,YOLOv5,and YOLOv8.The single image detection speed of D-YOLO is 20.36 ms,which is 37.06%,65.33%,45.22%,and 28.39%faster than those of various comparison models,respectively.Meanwhile,the attention range of image features of lining crack is increased through D-YOLO.The research results can provide new ide-as for the safety detection of lining during tunnel operation.
关键词
隧道工程/结构安全/可变形卷积网络/衬砌裂缝/YOLOv8Key words
tunnel engineering/structural safety/deformable convolutional network/lining crack/You Only Look Once v8(YOLOv8)引用本文复制引用
基金项目
陕西省交通运输厅交通科技项目(22-09K)
出版年
2024
NETL
NSTL
万方数据