From bebeb95aefd0097bbddfd815dbe96b9633a84680 Mon Sep 17 00:00:00 2001 From: Akash kr <97912085+A7-4real@users.noreply.github.com> Date: Fri, 4 Nov 2022 11:16:56 +0530 Subject: [PATCH] correct typo (keypont -> keypoint) --- dataset/keypoints-eval.htm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dataset/keypoints-eval.htm b/dataset/keypoints-eval.htm index f6c52a7..399634f 100644 --- a/dataset/keypoints-eval.htm +++ b/dataset/keypoints-eval.htm @@ -14,7 +14,7 @@

1.2. Object Keypoint Similarity

OKS = Σi[exp(-di2/2s2κi2)δ(vi>0)] / Σi[δ(vi>0)] -

The di are the Euclidean distances between each corresponding ground truth and detected keypoint and the vi are the visibility flags of the ground truth (the detector's predicted vi are not used). To compute OKS, we pass the di through an unnormalized Guassian with standard deviation sκi, where s is the object scale and κi is a per-keypont constant that controls falloff. For each keypoint this yields a keypoint similarity that ranges between 0 and 1. These similarities are averaged over all labeled keypoints (keypoints for which vi>0). Predicted keypoints that are not labeled (vi=0) do not affect the OKS. Perfect predictions will have OKS=1 and predictions for which all keypoints are off by more than a few standard deviations sκi will have OKS~0. The OKS is analogous to the IoU. Given the OKS, we can compute AP and AR just as the IoU allows us to compute these metrics for box/segment detection.

+

The di are the Euclidean distances between each corresponding ground truth and detected keypoint and the vi are the visibility flags of the ground truth (the detector's predicted vi are not used). To compute OKS, we pass the di through an unnormalized Guassian with standard deviation sκi, where s is the object scale and κi is a per-keypoint constant that controls falloff. For each keypoint this yields a keypoint similarity that ranges between 0 and 1. These similarities are averaged over all labeled keypoints (keypoints for which vi>0). Predicted keypoints that are not labeled (vi=0) do not affect the OKS. Perfect predictions will have OKS=1 and predictions for which all keypoints are off by more than a few standard deviations sκi will have OKS~0. The OKS is analogous to the IoU. Given the OKS, we can compute AP and AR just as the IoU allows us to compute these metrics for box/segment detection.

1.3. Tuning OKS

We tune the κi such that the OKS is a perceptually meaningful and easy to interpret similarity measure. First, using 5000 redundantly annotated images in val, for each keypoint type i we measured the per-keypoint standard deviation σi with respect to object scale s. That is we compute σi2=E[di2/s2]. σi varies substantially for different keypoints: keypoints on a person's body (shoulders, knees, hips, etc.) tend to have a σ much larger than on a person's head (eyes, nose, ears).