Skip to content

Latest commit

 

History

History
16 lines (14 loc) · 825 Bytes

File metadata and controls

16 lines (14 loc) · 825 Bytes

Realtime multi person pose estimation

  • Detects 2D pose of multiple people in the image.
  • Jointly trained to find the body parts and associations of the body parts with the individuals.
  • Earlier approaches were based on finding humans in the image, so depended on the number of persons in the image.
  • Also, if the human detector failed, everything fell apart.

Input and output

The system takes, as input, a color image of size w × h (Fig. 2a) and produces, as output, the 2D locations of anatomical keypoints for each person in the image.

Model

alt text

The model is split into two branches: one predicts the confidence maps for the body parts and the second branch predicts the affinity between those body parts.