Pose Estimation. Metrics.

(Photo taken from Pexels)

Metrics.

Percentage of Detected Joints (PDJ)

Intuitive presentation PDJ
  • di — the euclidian distance between ground truth keypoint and predicted keypoint;
  • bool(condition) — a function that returns 1 if the condition is true, 0 if it is false;
  • n —the number of key points on the image.

Object Keypoint Similarity (OKS)

  • di — the euclidian distance between ground truth keypoint and predicted keypoint;
  • sscale: the square root of the object segment area;
  • k —per-keypoint constant that controls fall off;

--

--

--

Computer Vision Engineer

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Deep Convolutional Neural Networks: Theory and Application in Geosciences

Finding the Best Wordle Opener with Machine Learning

How to get started with Machine Learning

Fundamentals of Deep Learning

What are the Must-Know algorithms for machine learning?

Decision Trees and Ensembling Methods

CDS Guest Editorial: Active Learning for Optimal Experiment Design in High Energy Physics

Linear Regression

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Alexander Stasiuk

Alexander Stasiuk

Computer Vision Engineer

More from Medium

Deep dive into Explainable AI: Current methods and challenges

AutoML Library for Regression : AutoKeras

ML Security with the Adversarial Robustness Toolbox

AI Application to Demonstrate K-Means Clustering Using H2O Wave