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 YOLOv8 Network Model.

More »

Fig 1 Expand

Fig 2.

Water surface interference factors.

More »

Fig 2 Expand

Fig 3.

Bi-level attention mechanism.

More »

Fig 3 Expand

Fig 4.

BiFormerBlock, C2fBF.

More »

Fig 4 Expand

Fig 5.

Comparison of trajectories of various optimization algorithms in a two-dimensional loss function space.

More »

Fig 5 Expand

Fig 6.

Comparison of Sophia and Adam in terms of mAP.

More »

Fig 6 Expand

Table 1.

Comparison among the tested models after applying the improved loss function.

More »

Table 1 Expand

Table 2.

Comparison among the tested models after applying the improved optimizer.

More »

Table 2 Expand

Table 3.

Results of the ablation experiment.

More »

Table 3 Expand

Fig 7.

Comparison between the mAPs of YOLOv8-SST and YOLOv8n.

More »

Fig 7 Expand

Table 4.

Performance comparison among different models.

More »

Table 4 Expand

Fig 8.

mAP@0.5 Changes Relative to the YOLO Series of Algorithms.

More »

Fig 8 Expand

Fig 9.

Visualization of water-surface object detection for different object sizes.

More »

Fig 9 Expand

Fig 10.

Visualization of water-surface object detection under different backgrounds.

More »

Fig 10 Expand

Fig 11.

Visualization comparison between YOLOv8n and YOLOv8-SST.

More »

Fig 11 Expand

Fig 12.

Model performance under diverse illumination environments.

More »

Fig 12 Expand