Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Dam surface crack detection based on SE-YOLOv7
Crack detection on the dam surface is the key link of the safety inspection of the hydropower station, but the complex environment has problems such as large interference and noise, complex and changeable shape and unbalanced pixels, which results in poor crack detection effect on the dam surface. We propose a dam surface crack detection method based on SE-YOLO and verify it through multiple scenarios. Crack detection on the dam surface is the key link of the safety inspection of the hydropower station, but the complex environment has problems such as large interference noise, complex and changeable shape, and pixel imbalance, which results in poor crack detection effect on the dam surface. A dam surface crack detection method based on SE-YOLO is proposed and validated through a variety of scenarios. By adding the attention mechanism SE between the large backbone of the YOLOv7 model and the Head, the feature extraction ability of the backbone network is enhanced to achieve a better detection effect. Experimental validation analysis was performed on the same dataset using FCN, U-Net, YOLOv7, SE-YOLOv7, and the method presented here. The experimental results show that the two-stage dam surface crack detection method based on SE-YOLO v7 can accurately detect the cracks, and effectively avoid the negative effects. Our mAP method and F1 method can reach 83.81% and 79.98%, respectively, and FPS reaches 77.86Hz, with a significant improvement compared with other models
Dam surface crack detection based on SE-YOLOv7
Crack detection on the dam surface is the key link of the safety inspection of the hydropower station, but the complex environment has problems such as large interference and noise, complex and changeable shape and unbalanced pixels, which results in poor crack detection effect on the dam surface. We propose a dam surface crack detection method based on SE-YOLO and verify it through multiple scenarios. Crack detection on the dam surface is the key link of the safety inspection of the hydropower station, but the complex environment has problems such as large interference noise, complex and changeable shape, and pixel imbalance, which results in poor crack detection effect on the dam surface. A dam surface crack detection method based on SE-YOLO is proposed and validated through a variety of scenarios. By adding the attention mechanism SE between the large backbone of the YOLOv7 model and the Head, the feature extraction ability of the backbone network is enhanced to achieve a better detection effect. Experimental validation analysis was performed on the same dataset using FCN, U-Net, YOLOv7, SE-YOLOv7, and the method presented here. The experimental results show that the two-stage dam surface crack detection method based on SE-YOLO v7 can accurately detect the cracks, and effectively avoid the negative effects. Our mAP method and F1 method can reach 83.81% and 79.98%, respectively, and FPS reaches 77.86Hz, with a significant improvement compared with other models
Dam surface crack detection based on SE-YOLOv7
Jabbar, M. A. (Herausgeber:in) / Lorenz, Pascal (Herausgeber:in) / Feng, Qian (Autor:in) / Li, Cuimei (Autor:in)
Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024) ; 2024 ; Kuala Lumpur, Malaysia
Proc. SPIE ; 13184
05.07.2024
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Dam Surface Crack Detection Based on CMAM-YOLOv7
| IEEE | 2024
YOLOv7 Deep Learning Model for Pavement Crack Detection Using Close Range Photogrammetry Dataset.
| DOAJ | 2024