基于深度学习的隧道衬砌多病害检测算法
|
宋娟,贺龙喜,龙会平
|
Deep learning-based algorithm for multi defect detection in tunnel lining
|
Juan SONG,Longxi HE,Huiping LONG
|
|
表 3 主干网络评价指标表 |
Tab.3 Backbone network evaluation indicators |
|
主干网络 | 裂缝 | | 渗漏水 | | 衬砌脱落 | F1/% | mAP/% | f1/% | AP/% | f1/% | AP/% | f1/% | AP/% | MobileNet | 74.43 | 75.54 | | 74.85 | 75.74 | | 65.66 | 62.33 | 71.65 | 71.20 | GhostNet | 73.64 | 73.60 | 74.12 | 75.31 | 65.32 | 60.87 | 71.03 | 69.93 | ResNet | 74.56 | 77.52 | 74.48 | 75.76 | 66.84 | 65.30 | 71.96 | 72.86 | Swin transformer | 74.48 | 76.97 | 75.03 | 78.61 | 66.91 | 64.49 | 72.14 | 73.36 | MobileViT | 75.83 | 79.58 | 76.32 | 79.62 | 68.32 | 65.24 | 73.49 | 74.81 |
|
|
|