A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Computer vision-based concrete crack detection using U-net fully convolutional networks
Abstract For the first time, U-Net is adopted to detect the concrete cracks in the present study. Focal loss function is selected as the evaluation function, and the Adam algorithm is applied for optimization. The trained U-Net is able of identifying the crack locations from the input raw images under various conditions (such as illumination, messy background, width of cracks, etc.) with high effectiveness and robustness. In addition, U-Net based concrete crack detection method proposed in the present study is compared with the DCNN-based method, and U-Net is found to be more elegant than DCNN with more robustness, more effectiveness and more accurate detection. Furthermore, by examining the fundamental parameters representing the performance of the method, the present U-Net is found to reach higher accuracy with smaller training set than the previous FCNs.
Highlights Concrete crack detection method using U-Net is proposed. U-Net is of more robustness and more effectiveness than CNN-based method. Only 57 images in the training and validation set can provide a good model for detecting the cracks. Precisions of the model trained by 57 images can reach 0.9 for different complex situations. U-Net can reach higher accuracy with smaller training set than the previous FCNs.
Computer vision-based concrete crack detection using U-net fully convolutional networks
Abstract For the first time, U-Net is adopted to detect the concrete cracks in the present study. Focal loss function is selected as the evaluation function, and the Adam algorithm is applied for optimization. The trained U-Net is able of identifying the crack locations from the input raw images under various conditions (such as illumination, messy background, width of cracks, etc.) with high effectiveness and robustness. In addition, U-Net based concrete crack detection method proposed in the present study is compared with the DCNN-based method, and U-Net is found to be more elegant than DCNN with more robustness, more effectiveness and more accurate detection. Furthermore, by examining the fundamental parameters representing the performance of the method, the present U-Net is found to reach higher accuracy with smaller training set than the previous FCNs.
Highlights Concrete crack detection method using U-Net is proposed. U-Net is of more robustness and more effectiveness than CNN-based method. Only 57 images in the training and validation set can provide a good model for detecting the cracks. Precisions of the model trained by 57 images can reach 0.9 for different complex situations. U-Net can reach higher accuracy with smaller training set than the previous FCNs.
Computer vision-based concrete crack detection using U-net fully convolutional networks
Liu, Zhenqing (author) / Cao, Yiwen (author) / Wang, Yize (author) / Wang, Wei (author)
Automation in Construction ; 104 ; 129-139
2019-04-06
11 pages
Article (Journal)
Electronic Resource
English
Crack detection , U-net , FCN , Vision-based , Data-driven
Structural crack detection using deep learning–based fully convolutional networks
| SAGE Publications | 2019
Autonomous concrete crack detection using deep fully convolutional neural network
| British Library Online Contents | 2019