Table 3 Comparative experiment results for different models.
Model | Precision (%) | Recall (%) | F1 (%) | mAP50 (%) | mAP50:95 (%) | Parameters(M) | GFlops | FPS |
|---|---|---|---|---|---|---|---|---|
Yolov3-tiny | 39.1 | 24.3 | 22.5 | 23.6 | 13.2 | 9.52 | 14.3 | 17 |
Yolov5n | 44.5 | 33.2 | 38.0 | 32.9 | 19.1 | 2.18 | 5.8 | 23 |
Yolov5s | 51.1 | 38.1 | 43.7 | 39.3 | 23.4 | 7.81 | 18.8 | 26 |
Yolov5m | 47.7 | 36.8 | 37.0 | 39.4 | 23 | 20.88 | 48 | 14 |
Yolov5l | 50.7 | 38.6 | 43.9 | 41.4 | 24.6 | 46.15 | 107.8 | 8 |
Yolov5x | 52.1 | 40.4 | 41 | 43 | 26 | 20.39 | 86.23 | 5 |
Yolov6s | 40.3 | 30.5 | 30.2 | 30.2 | 17.7 | 4.15 | 11.5 | - |
Yolov7tiny | 47.6 | 37.3 | 41.8 | 35.8 | 18.8 | 6.04 | 13.3 | 32 |
Yolov8n | 45 | 33 | 33.1 | 38.1 | 19.2 | 2.68 | 6.8 | 25 |
Yolov8s | 50.7 | 37.9 | 43.3 | 39.1 | 23.4 | 9.83 | 23.4 | 18 |
Yolov8m | 53.3 | 41.1 | 46.4 | 42.5 | 26 | 23.2 | 67.5 | 8 |
Yolov9s | 52 | 38 | 39.4 | 43.9 | 23.8 | 61.9 | 22.1 | 22 |
Yolov10n | 45.0 | 34.5 | 39.1 | 34.5 | 19.9 | 2.26 | 6.5 | 36 |
Yolov10s | 52.7 | 38 | 44.0 | 39.8 | 23.8 | 7.22 | 21.4 | 32 |
Yolov10m | 55.1 | 42.1 | 47.4 | 44.2 | 26.9 | 15.31 | 58.9 | 30 |
Yolov11n | 42.7 | 32.7 | 37.3 | 32.2 | 18.6 | 2.61 | 6.5 | 35 |
Yolov11s | 49.9 | 38.7 | 43.5 | 39.4 | 23.6 | 9.41 | 21.3 | 34 |
Yolov11m | 55.7 | 42.5 | 48.2 | 44.1 | 27.2 | 20.03 | 67.7 | 28 |
Yolov11L | 55.5 | 43 | 48.3 | 44.4 | 27.5 | 25.28 | 86.6 | 20 |
rtdetr-r18 | 57.2 | 40 | 47.1 | 41.4 | 25.1 | 20 | 57 | 60 |
EL-YOLO40 | 48.8 | 40.3 | 43 | 42.9 | 24.8 | 6.7 | 1.08 | 35 |
YOLOv8-QSD41 | 44.2 | 38.6 | 34.2 | 34.6 | 16.8 | - | - | - |
Drone-YOLO5 | - | - | 40 | 41.4 | 25.1 | - | 5.35 | - |
CPDD-YOLOv842 | 51.7 | 41.7 | 46.1 | 41.0 | 23.5 | 206 | 141.9 | 22 |
LRDS-YOLO | 53.3 | 41.6 | 46.0 | 43.6 | 26.6 | 4.17 | 24.1 | 31 |
