Research on Aided Judgment of Rural Sports Posture Based on Deep Learning

Table 8

Traditional pose detection algorithm.

Target number	Goal 1	Goal 2	Goal 3	Goal 4	Goal 5	Goal 6	Goal 7	Goal 8
Total number of frames	204	204	204	204	204	204	204	204
Number of missed inspections	9	11	12	10	13	8	7	9
Missed detection rate (%)	4.6	5.4	5.9	4.9	6.4	3.9	3.4	4.4
Action accuracy	95.0%	93.6%	94.7%	94.6%	93.6%	93.9%	94.0%	95.1%
Recording time (minutes)	5.1	5.3	5.5	5.4	5.5	5.7	5.9	5.8