Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Tunnel lining crack detection model based on improved YOLOv5
https://orcid.org/0000-0001-6625-4087
https://orcid.org/0000-0002-3805-814X
Highlights: An improved YOLOv5 model for tunnel crack detection is proposed. Model overcomes low light, low contrast and high noise challenges in tunnels. Improved model achieves 90% detection accuracy while realizing real-time detection. Improved model can be applied to practical engineering through field validation.
Abstract An improved real-time tunnel lining crack detection model based on YOLOv5 is proposed. This model maintains high precision and accuracy crack detection in low-light, low-contrast and high-noise environments by introducing several effective data augmentation techniques as well as semantic context encoding (SCE) and detail preserving encoding (DPE) at the head of the network structure. It achieves 90 % precision, 91 % recall, and 92 % mAP@50. The model demonstrates better detection performance than YOLOv4-tiny, YOLOv5s, YOLOv8s, and traditional threshold segmentation method, especially in complex environments to reduce misdetection and omission. The average detection time is only 12 ms per image, demonstrating the feasibility of its real-time application. The robust and generalization performance of the model is validated in specific engineering applications, showing great potential for improving detection efficiency, cost-effectiveness, and reliability in tunnel safety assessment and disasters management.
Tunnel lining crack detection model based on improved YOLOv5
https://orcid.org/0000-0001-6625-4087
https://orcid.org/0000-0002-3805-814X
Highlights: An improved YOLOv5 model for tunnel crack detection is proposed. Model overcomes low light, low contrast and high noise challenges in tunnels. Improved model achieves 90% detection accuracy while realizing real-time detection. Improved model can be applied to practical engineering through field validation.
Abstract An improved real-time tunnel lining crack detection model based on YOLOv5 is proposed. This model maintains high precision and accuracy crack detection in low-light, low-contrast and high-noise environments by introducing several effective data augmentation techniques as well as semantic context encoding (SCE) and detail preserving encoding (DPE) at the head of the network structure. It achieves 90 % precision, 91 % recall, and 92 % mAP@50. The model demonstrates better detection performance than YOLOv4-tiny, YOLOv5s, YOLOv8s, and traditional threshold segmentation method, especially in complex environments to reduce misdetection and omission. The average detection time is only 12 ms per image, demonstrating the feasibility of its real-time application. The robust and generalization performance of the model is validated in specific engineering applications, showing great potential for improving detection efficiency, cost-effectiveness, and reliability in tunnel safety assessment and disasters management.
Tunnel lining crack detection model based on improved YOLOv5
https://orcid.org/0000-0001-6625-4087
https://orcid.org/0000-0002-3805-814X
Highlights: An improved YOLOv5 model for tunnel crack detection is proposed. Model overcomes low light, low contrast and high noise challenges in tunnels. Improved model achieves 90% detection accuracy while realizing real-time detection. Improved model can be applied to practical engineering through field validation.
Abstract An improved real-time tunnel lining crack detection model based on YOLOv5 is proposed. This model maintains high precision and accuracy crack detection in low-light, low-contrast and high-noise environments by introducing several effective data augmentation techniques as well as semantic context encoding (SCE) and detail preserving encoding (DPE) at the head of the network structure. It achieves 90 % precision, 91 % recall, and 92 % mAP@50. The model demonstrates better detection performance than YOLOv4-tiny, YOLOv5s, YOLOv8s, and traditional threshold segmentation method, especially in complex environments to reduce misdetection and omission. The average detection time is only 12 ms per image, demonstrating the feasibility of its real-time application. The robust and generalization performance of the model is validated in specific engineering applications, showing great potential for improving detection efficiency, cost-effectiveness, and reliability in tunnel safety assessment and disasters management.
Tunnel lining crack detection model based on improved YOLOv5
Duan, Shuqian (Autor:in) / Zhang, Minghuan (Autor:in) / Qiu, Shili (Autor:in) / Xiong, Jiecheng (Autor:in) / Zhang, Hao (Autor:in) / Li, Chenyang (Autor:in) / Jiang, Quan (Autor:in) / Kou, Yongyuan (Autor:in)
14.03.2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Tunnel lining crack detection model based on improved YOLOv5
| Elsevier | 2024
Real-time tunnel lining crack detection based on an improved You Only Look Once version X algorithm
| Taylor & Francis Verlag | 2023