Nose and foot coordinates using key-point R-CNN and DensePose

Asked Jan 13 '20 at 07:04

Active Jan 13 '20 at 08:10

Viewed 228 times

Given an image, say, this, I am using the Key-Point R-CNN (from detectron2) to get the coordinates of the nose and either foot. Using this code, I get a 3D-reconstruction. DensePose changes the person's pose (as shown in the previous link). Using the 3D model and the key-points, how can I get the 3D coordinates of the nose and feet? (As of right now, they do not match). I used the projection of the model to the Y-Z plane then tried looking for the right and left most maxima but couldn't find a good enough algorithm.

Thanks!

edited Jan 13 '20 at 08:10

asked Jan 13 '20 at 07:04

Itamar Safriel

You can raise this as an issue in Github from which you are taking the code. This looks a logical doubt rather than any error – Abhik Sarkar Jan 13 '20 at 07:07
I already did. I got no answer so I tried here. – Itamar Safriel Jan 14 '20 at 09:08

Nose and foot coordinates using key-point R-CNN and DensePose

0 Answers0