Table 4 The experimental results of head network improvement.
From: YOLOFM: an improved fire and smoke object detection algorithm based on YOLOv5n
Model | Precision (%) | Recall (%) | mAP50 (%) | mAP50-95 (%) | FPS (%) | Params (MB) | GFLOPs(G) |
|---|---|---|---|---|---|---|---|
YOLOv5n | 91.8 | 90.9 | 95.3 | 66.8 | 80.90 | 6.72 | 4.1 |
YOLOX_DH | 93.3 | 92.7 | 96.2 | 71.6 | 39.91 | 34.20 | 44.2 |
YOLOv6_DH | 93.0 | 90.1 | 95.5 | 68.0 | 68.32 | 7.25 | 4.6 |
YOLOCS_ADH | 92.6 | 92.2 | 95.9 | 70.3 | 43.54 | 22.78 | 20.3 |
YOLOFM_NADH | 93.8 | 92.9 | 96.2 | 70.6 | 65.20 | 13.87 | 9.3 |
