Real-Time Fire Detection Method Based on Computer Vision for Electric Vehicle Charging Safety Monitoring

Table 3

Comparison of YOLOv5 algorithm detection indicators under different parameters.

Network models	Precision		Recall		F1		mAP (%)
	Fire (%)	Smoke (%)	Fire (%)	Smoke (%)	Fire	Smoke
YOLOv5-s	92.27	93.73	80.88	91.22	0.86	0.92	92.67
YOLOv5-m	89.96	93.85	83.07	93.13	0.86	0.93	93.77
YOLOv5-l	89.74	94.12	83.67	91.60	0.87	0.93	93.99
YOLOv5-x	83.48	90.28	76.49	85.11	0.80	0.88	87.08