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 the YOLOv8 model.

More »

Fig 1 Expand

Fig 2.

MFDA-YOLO network structure.

More »

Fig 2 Expand

Fig 3.

Structural diagram of the AIFI module.

More »

Fig 3 Expand

Fig 4.

The SPD-Conv specific process when scale = 2.

More »

Fig 4 Expand

Fig 5.

Details of the C-OKM module.

(a): C-OKM. (b): Omni-Kernel module. (c): DCAM. (d): FASM.

More »

Fig 5 Expand

Fig 6.

The structure of the DADH.

More »

Fig 6 Expand

Fig 7.

The principle of the task decomposition.

More »

Fig 7 Expand

Table 1.

Ablation study on hyperparameters of WIoUv3.

More »

Table 1 Expand

Table 2.

Ablation experiment results of modules on the VisDrone2019-DET-Test.

More »

Table 2 Expand

Table 3.

Results of different models on the VisDrone2019-DET-Test.

More »

Table 3 Expand

Fig 8.

Confusion matrix of YOLOv8n.

More »

Fig 8 Expand

Fig 9.

Confusion matrix of MFDA-YOLO.

More »

Fig 9 Expand

Table 4.

Results of different models on the HIT-UAV.

More »

Table 4 Expand

Table 5.

Results of different models on the NWPU VHR-10.

More »

Table 5 Expand

Fig 10.

Comparison of detection results across different models on the Visdrone2019 dataset. (The black box demonstrates the MFDA-YOLO’s ability to reduce missed and false detections).

More »

Fig 10 Expand

Fig 11.

Heat map comparison among different models on the HIT-UAV dataset. (The black bounding box highlights that MFDA-YOLO produces markedly more concentrated heat-maps on small objects).

More »

Fig 11 Expand