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.

Overall Architecture and Inference Pipeline of the MTF-NET Detection Framework.

More »

Fig 1 Expand

Fig 2.

Overall architecture diagrams of CAF and CFF.

More »

Fig 2 Expand

Fig 3.

Overall architectural diagram of CFF and CAF in MTF-NET.

More »

Fig 3 Expand

Fig 4.

Detailed Architecture Diagram of MKDFN.

More »

Fig 4 Expand

Fig 5.

Overall structure diagram of HIEP.

More »

Fig 5 Expand

Fig 6.

Internal Structure Diagram of HFFU.

More »

Fig 6 Expand

Table 1.

Comparison of YOLOv11n and MTF-NET on different classes.

More »

Table 1 Expand

Table 2.

Comparative Analysis of Different Algorithms on the VisDrone2019 Test Set.

More »

Table 2 Expand

Fig 7.

Comparative Analysis of Various Detectors on the VisDrone2019 Dataset.

More »

Fig 7 Expand

Table 3.

Comparative experiments evaluating various approaches for small-target enhancement.

More »

Table 3 Expand

Table 4.

Comparative Analysis of the Effectiveness of Different Loss Functions.

More »

Table 4 Expand

Table 5.

Comparative Analysis of Different IoU Functions.

More »

Table 5 Expand

Table 6.

Ablation Study Results on VisDrone2019 Dataset with Various Components and Losses.

More »

Table 6 Expand

Fig 8.

Comparison of detection results between YOLOv11n and MTF-NET under different scenarios.

Rows (a), (b), (c), and (d) correspond to aerial low-light scenes, occlusion scenes, densely populated object scenes, and nighttime scenes, respectively. Columns (e), (f), and (g) represent the original images, detection results from YOLOv11n, and detection results from MTF-NET, respectively.

More »

Fig 8 Expand

Fig 9.

Heatmap visualizations of YOLOv11n and MTF-NET under different viewpoints.

Rows (a) and (b) correspond to nighttime scenes and drone-based aerial small-object scenes, respectively. Columns (c), (d), and (e) represent the original images, heatmaps generated by YOLOv11n, and heatmaps generated by MTF-NET, respectively.

More »

Fig 9 Expand

Fig 10.

A comparison of detection performance between YOLOv11n and MTF-NET on the UA-DETRAC-G2 dataset (a) and the original HazyDet dataset (b).

Row (a) presents sampled visualized detection outcomes for the UA-DETRAC-G2 dataset, while row (b) illustrates corresponding results for the HazyDet dataset. In both cases, column (c) displays the original images, column (d) presents the detection results from YOLOv11n, and column (e) shows the outcomes achieved by MTF-NET.

More »

Fig 10 Expand

Table 7.

Generalization experiments on the UA-DETRAC-G2 dataset.

More »

Table 7 Expand

Table 8.

Generalization experiments conducted on the test set of the original HazyDet dataset.

More »

Table 8 Expand