Percentage of correct keypoints (PCK)

PCK is used as an accuracy metric that measures if the predicted keypoint and the true joint are within a certain distance threshold. The PCK is usually set with respect to the scale of the subject, which is enclosed within the bounding box. The threshold can either be:

- PCKh@0.5 is when the threshold = 50% of the head bone link
- PCK@0.2 = Distance between predicted and true joint < 0.2 * torso diameter
- Sometimes 150 mm is taken as the threshold.
- It alleviates the shorter limb problem since shorter limbs have smaller torsos and head bone links.
- PCK is used for 2D and 3D (PCK3D)

Trustworthy AI Relevance

This metric addresses Robustness and Transparency by quantifying relevant system properties. Robustness: PCK measures how often predicted keypoints fall within an acceptable spatial tolerance of ground truth, so it directly quantifies model accuracy and consistency under different conditions (e.g., noise, occlusion, viewpoint change, domain shift). Tracking PCK across datasets, perturbations, and time helps evaluate and improve a model's resilience and reliability.