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.

The JLU UGV.

More »

Fig 1 Expand

Fig 2.

The hunting process of grey wolves.

More »

Fig 2 Expand

Fig 3.

The general structure of BRPN.

More »

Fig 3 Expand

Fig 4.

The network of the synthesized feature sampling strategy.

More »

Fig 4 Expand

Fig 5.

The enhanced pooling strategy.

More »

Fig 5 Expand

Fig 6.

The framework of the EPN.

More »

Fig 6 Expand

Fig 7.

The relationship between the GA and the parameters.

More »

Fig 7 Expand

Fig 8.

The process of SVM parameter optimization based on the GA.

More »

Fig 8 Expand

Fig 9.

The graph of with different values of η.

More »

Fig 9 Expand

Fig 10.

The relationship between the GWO and loss function coefficients.

More »

Fig 10 Expand

Fig 11.

Flowchart of the parameter optimization process with GWO.

More »

Fig 11 Expand

Table 1.

Dataset information.

More »

Table 1 Expand

Table 2.

GA parameters.

More »

Table 2 Expand

Table 3.

GWO parameters.

More »

Table 3 Expand

Table 4.

BRPN parameters.

More »

Table 4 Expand

Table 5.

Detection results on the PASCAL VOC 2007 test set.

More »

Table 5 Expand

Table 6.

Detection results on PASCAL VOC 2012 test set.

More »

Table 6 Expand

Fig 12.

Small-object detection results on the PASCAL VOC 2007 and VOC 2012 test sets.

More »

Fig 12 Expand

Fig 13.

Recall versus IoU threshold on the VOC 2007 test set.

Left: 150 region proposals. Middle: 450 region proposals. Right: 850 region proposals.

More »

Fig 13 Expand

Fig 14.

ROC curves of the compared methods.

More »

Fig 14 Expand

Table 7.

Experimental results over the novel enhanced pooling network.

More »

Table 7 Expand

Fig 15.

The optimization process for the different coefficients.

More »

Fig 15 Expand

Table 8.

Runtime data for the different coefficients.

More »

Table 8 Expand

Table 9.

Experiment results of the training error.

More »

Table 9 Expand

Table 10.

Experimental results over the novel loss function optimized by the GWO.

More »

Table 10 Expand

Table 11.

Comparison between the softmax, SVM and GA-SVM classifiers.

More »

Table 11 Expand

Table 12.

Detection results on the KITTI dataset.

More »

Table 12 Expand

Table 13.

Detection frame rate of the different methods on the PASCAL VOC 2007 test set.

More »

Table 13 Expand