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 overall structure of DPCNet.

More »

Fig 1 Expand

Fig 2.

The structure of the DPCP block.

More »

Fig 2 Expand

Fig 3.

The structure of the DSFI block.

More »

Fig 3 Expand

Fig 4.

The architecture of detection head.

(a) Baseline Head, (b) DPD Head.

More »

Fig 4 Expand

Table 1.

Ablation experiment results on HIT-UAV dataset.

More »

Table 1 Expand

Table 2.

Targeted ablation results of cross-branch interaction in the DPD head on HIT-UAV dataset.

More »

Table 2 Expand

Table 3.

Comparison of bounding box regression loss functions within DPCNet.

More »

Table 3 Expand

Table 4.

Comparison of detection performance on the HIT-UAV test set.

More »

Table 4 Expand

Table 5.

Comparison of detection performance on the VisDrone2019 test set.

More »

Table 5 Expand

Table 6.

Runtime comparison between DPCNet and YOLO11n.

More »

Table 6 Expand

Fig 5.

Radar chart of small-object proportions in the VisDrone2019 dataset.

More »

Fig 5 Expand

Fig 6.

Radar chart of small-object proportions in the HIT-UAV dataset.

More »

Fig 6 Expand

Fig 7.

Recall-rate difference curves for small objects across categories on VisDrone2019.

More »

Fig 7 Expand

Fig 8.

Recall-rate difference curves for small objects across categories on HIT-UAV.

More »

Fig 8 Expand

Fig 9.

Small-object detection comparison on VisDrone2019.

More »

Fig 9 Expand

Fig 10.

Small-object detection comparison on HIT-UAV.

More »

Fig 10 Expand

Fig 11.

Heatmaps for small-object detection on VisDrone2019.

More »

Fig 11 Expand

Fig 12.

Heatmaps for small-object detection on HIT-UAV.

More »

Fig 12 Expand

Fig 13.

Recall improvement for small objects under low illumination on VisDrone2019.

More »

Fig 13 Expand

Fig 14.

Visual comparison of small-object detection under low illumination.

More »

Fig 14 Expand

Fig 15.

Recall comparison in three challenging subsets.

More »

Fig 15 Expand

Fig 16.

Representative failure cases of DPCNet.

(a) Dense daytime traffic scene. (b) Low-illumination night scene.

More »

Fig 16 Expand