Table 8 Class-wise results of validation and test.

From: Automated non-PPE detection on construction sites using YOLOv10 and transformer architectures for surveillance and body worn cameras with benchmark datasets

Datasets

Metrics

Class

Non-helmet

Non-mask

Non-vest

Non-glove

Non-shoes

mAP

Validation

AP50

92.35

87.95

87.07

85.32

83.56

87.25

AP50:95

68.29

65.04

64.39

63.09

61.79

64.52

IOU

87.39

83.23

82.39

80.73

79.06

82.56

AP_S

64.5

61.43

60.82

59.59

58.36

60.94

AP_M

89.9

85.61

84.76

83.05

81.33

84.93

AP_L

96.95

92.33

91.41

89.56

87.71

91.59

Test

AP50

92.4

88.17

87.17

85.36

83.48

87.32

AP50:95

68.23

65.43

64.85

62.97

62.08

64.71

IOU

87.46

83.66

81.93

80.32

78.58

82.39

AP_S

64.78

61.8

61.3

59.89

58.32

61.22

AP_M

89.52

85.75

84.4

83.49

81.35

84.9

AP_L

96.71

92.6

91.37

89.63

87.23

91.51

Back to article page