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.

Structure of SSD.

More »

Fig 1 Expand

Fig 2.

Structure of ISSD.

More »

Fig 2 Expand

Fig 3.

Three typical cases of convolution kernel shifting of conventional convolution.

Group A is the conventional distribution, Group B is the distribution after arbitrary migration, Group C is the distribution after scaling transformation and Group D is the distribution after rotational transformation.

More »

Fig 3 Expand

Fig 4.

Schematic diagram of depth separable convolution.

More »

Fig 4 Expand

Fig 5.

Schematic diagram of the depth separable deformable convolution.

More »

Fig 5 Expand

Fig 6.

Schematic diagram of the inception structure.

Group A represents the structure of the original inception and Group B represents the structure of the improved inception.

More »

Fig 6 Expand

Fig 7.

Structure of the feature recalibration module.

More »

Fig 7 Expand

Table 1.

Number of different samples in the WCD dataset.

More »

Table 1 Expand

Table 2.

Specific index parameters of the workstation.

More »

Table 2 Expand

Fig 8.

Curves of training loss with different learning epochs.

More »

Fig 8 Expand

Fig 9.

Comparison of output results at different epochs.

The green boxes locate the missing detection parts of the detection results and the red boxes locate the false detection parts of the detection results.

More »

Fig 9 Expand

Table 3.

Network parameter setting.

More »

Table 3 Expand

Table 4.

Validation results of components in the ISSD.

More »

Table 4 Expand

Table 5.

The results of different networks on the WCD dataset.

More »

Table 5 Expand

Table 6.

The computational efficiency and computational complexity of different networks.

More »

Table 6 Expand

Fig 10.

Visualization of detection results of compared networks on the WCD dataset.

More »

Fig 10 Expand

Fig 11.

The visualization of detection results of compared networks in real images.

More »

Fig 11 Expand