Table 1 Object detection model performance is evaluated using precision, recall, and mean average precision (mAP)

From: From video to vital signs: a new method for contactless multichannel seismocardiography

Classes

Precision (%)

Recall (%)

mAP@.5 (%)

mAP@.5:.95 (%)

QR code

100

100

99.6

81.5

2QR areaa

99.4

99.9

99.6

80.5

All (mAP)

99.7

99.9

99.6

81.0

  1. Precision and recall are calculated based on the best confidence score, which is 85.4%. The mAP@.5 is computed at an Intersection over Union (IoU) threshold of 0.5. The mAP@.5:.95 shows the mAP calculated over a range of IoU thresholds from 0.5 to 0.95, with a step size of 0.05.
  2. a2QR area: area between two adjacent QR codes enclosed by the QR code borders.
Back to article page