Table 9 Comparative object detection performance: YOLOv11 vs. ViT.

From: Design and research of bridge collision avoidance system based on camera calibration technology and motion detection

Condition

Model

Precision (%)

Recall (%)

mAP@0.5 (%)

mAP@0.75 (%)

IoU (%)

Daylight

YOLOv11

94.6

91.2

93.1

88.5

86.9

ViT-B/16

95.4

89.8

91.7

89.6

88.2

Night

YOLOv11

90.8

87.3

89.2

84.0

83.5

ViT-B/16

92.1

85.7

87.6

85.2

85.9

Rain/Fog

YOLOv11

88.2

82.5

85.7

79.1

80.4

ViT-B/16

89.6

81.2

84.1

81.5

82.8

Back to article page