Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Technical flow chart of damage detection.

More »

Fig 1 Expand

Table 1.

Network structure table of the classifier.

More »

Table 1 Expand

Fig 2.

The network structure of SegFormer [45].

More »

Fig 2 Expand

Fig 3.

Sample dataset.

More »

Fig 3 Expand

Table 2.

Composition of the dataset.

More »

Table 2 Expand

Fig 4.

The training curves of classification model. (a) Concrete spalling classifier. (b) Crack classifier.

More »

Fig 4 Expand

Fig 5.

Example of classification results of the original image.

More »

Fig 5 Expand

Fig 6.

The training curves of segmentation model.

(a) Concrete spalling segmentation. (b) Crack segmentation.

More »

Fig 6 Expand

Fig 7.

Example of segmentation results.

More »

Fig 7 Expand

Fig 8.

The skeleton line of crack binary image.

More »

Fig 8 Expand

Fig 9.

Crack size information.

More »

Fig 9 Expand

Fig 10.

Confusion matrix of safety evaluation.

More »

Fig 10 Expand

Table 3.

Hyperparameter for each model.

More »

Table 3 Expand

Table 4.

Comparative experiment.

More »

Table 4 Expand

Fig 11.

Confusion matrix of several comparison models.

(a) GB. (b) SVM. (c) MLP. (d) DT.

More »

Fig 11 Expand