Head pose estimation

This repo shows how to estimate human head pose from videos using TensorFlow and OpenCV.

Head-pose-estimationv

Head-pose-estimation

Dependence

  • TensorFlow 1.4
  • OpenCV 3.3
  • Python 3

The code is tested under Ubuntu 16.04.

How it works

There are three major steps:

  1. Face detection. A face detector is adopted to provide a face box containing a human face. Then the face box is expanded and transformed to a square to suit the needs of later steps.

  2. Facial landmark detection. A custom trained facial landmark detector based on TensorFlow is responsible for output 68 facial landmarks.

  3. Pose estimation. Once we got the 68 facial landmarks, a mutual PnP algorithms is adopted to calculate the pose.

Miscellaneous

  • The marks is detected frame by frame, which result in small variance between adjacent frames. This makes the pose unstaible. A Kalman filter is used to solve this problem, you can draw the original pose to observe the difference.

  • The 3D model of face comes from OpenFace, you can find the original file here.

GitHub