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.

Network structure of SSD model.

More »

Fig 1 Expand

Fig 2.

Shufflenet_V2 network structure.

More »

Fig 2 Expand

Fig 3.

Shufflenet_V2 network main block (a) DownSampling block (b) Normal block.

More »

Fig 3 Expand

Table 1.

The architecture of improved Shufflenet_v2 network.

More »

Table 1 Expand

Fig 4.

Schematic diagram of the position of real Box B and prediction box BGT.

More »

Fig 4 Expand

Fig 5.

Improved SSD_Shufflenet_V2 network structure.

More »

Fig 5 Expand

Fig 6.

Loss calculation.

More »

Fig 6 Expand

Fig 7.

Belt conveyor experimental platform.

More »

Fig 7 Expand

Table 2.

The training HyperParameters adopted.

More »

Table 2 Expand

Fig 8.

LablImg software annotates images.

More »

Fig 8 Expand

Fig 9.

The confusion matrices: (a) the models of enhanced Shufflenet_v2; (b) SqueezeNet model; (c)Densenet model; (d)MobileNet_V2 model.

More »

Fig 9 Expand

Table 3.

Comparison and verification of various lightweight convolutional neural networks.

More »

Table 3 Expand

Fig 10.

The object detection diagram: (a) the models of this paper; (b) without the CIoU model; (c) SSD model.

More »

Fig 10 Expand

Fig 11.

Accuracy rate curve of the method proposed in this paper.

More »

Fig 11 Expand

Table 4.

Performance comparison between other methods and our model.

More »

Table 4 Expand

Fig 12.

Video target recognition verification of this model.

More »

Fig 12 Expand