Figure 1.
ATD-YOLO Network Structure
Figure 2.
Framework of image measuring system [14]
Figure 3.
C3F structural schematic diagram
Figure 4.
CARAFE upsampling calculation flowchart
Figure 5.
EMA Attention Mechanism
Figure 6.
GSConv Module
Figure 7.
VoVGCSP Module
Figure 8.
The positions of GSConv and VOVGCSP modules
TABLE I.
Experimental Setup Configuration
| Name | Environment Configuration |
|---|---|
| System Environment | Ubuntu 22.04 |
| CPU | AMD Ryzen 9 5950X |
| GPU | RTX 4060 Ti 16GB |
| Deep Learning Framework | Pytorch 1.13.1 |
| IDE | CUDA 11.7 |
TABLE II.
Origin of the Dataset and Quantity of Images
| Dataset | Number of Images |
|---|---|
| Det-Fly | 3893 |
| Drone-vs-Bird | 3959 |
| Real World | 1525 |
| Multi-view drone tracking | 3447 |
| DUT anti-UAV | 3639 |
| Anti-UAV | 2767 |
Figure 9.
Length and Width Distribution Chart of the Anti-Mini Drone Dataset
Figure 10.
Samples of simple background from Anti-Mini Drone
Figure 11.
Samples of complex background from Anti-Mini Drone
Figure 12.
PR curves for various feature extraction modules (IOU=0.5)
TABLE III.
Contrast experiment of attention module
| Module | mAP.5/% | GFLOP /G | Params/106 | FPS |
|---|---|---|---|---|
| C3 | 92.2 | 15.8 | 7.01 | 68.79 |
| C3F | 92.3 | 13.8 | 6.33 | 75.05 |
| C2f | 93.1 | 19.4 | 8.25 | 55.38 |
| C2f-Faster | 91.9 | 14.5 | 6.58 | 77.57 |
Figure 13.
PR curves for various feature extraction modules (IOU=0.5)
TABLE V.
Results of ablation experiments
| YOLOv5s | C3F | EMA | CARFE | Slim-Neck | Params/10 6 | GFLOP/G | mAP.5/% | FPS |
|---|---|---|---|---|---|---|---|---|
| √ | 7.01 | 15.8 | 92.2 | 68.79 | ||||
| √ | √ | 6.33 | 13.8 | 92.3 | 75.05 | |||
| √ | √ | √ | 6.38 | 14.1 | 92.7 | 69.83 | ||
| √ | √ | √ | √ | 6.40 | 14.1 | 93.1 | 67.85 | |
| √ | √ | √ | √ | √ | 5.23 | 11.0 | 92.8 | 75.35 |
Figure 14.
Model PR curve (IOU=0.5)
TABLE VI.
Mainstream Algorithm Comparative Experiment Results
| Module | Params/106 | GFLOP/G | AP.5/% | FPS |
|---|---|---|---|---|
| YOLOv3 Tiny | 8.66 | 12.9 | 79.1 | 166.67 |
| YOLOv5s | 7.01 | 15.9 | 92.2 | 68.79 |
| YOLOv7 Tiny | 6.01 | 13.2 | 88.4 | 63.30 |
| YOLOv8s | 11.12 | 28.4 | 89.0 | 109.89 |
| ATD-YOLO | 5.23 | 11.0 | 92.8 | 75.35 |
Figure 15.
PR curves of mainstream algorithms on the test set (IOU=0.5)
Figure 16.
Object detection outcomes in diverse scenarios
Figure 17.
Object detection outcomes in a consistent scenario