Skip to content
Head pose estimation algorithm from single depth Kinect 2 frame
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
DictionaryReg.mat
FactSheet.pdf
HeadPoseEstim_CMTech.m
LmkRegress.mat
README.txt
Read_dFL_Landmarks.m
ShapeContext3D.m
ShapeContext_PreCompute.m
depthToCloud.m
estimAngles_DiccReg.m
mesh_3dSC_FixedView.m
ply_write.m
ply_writeMesh.m
readNPY.m
readNPYheader.m
srilf3dFL_F1_K2_155_BQ3.cfg
vtkClearDisconnecteedPts.exe

README.txt

This is an implementation of Head pose estimation algorithm from single depth Kinect 2 frame.
More detailed information could be found at 
http://fsukno.atspace.eu/Research.htm#HeadPoseChall17

=======================
The algorithms are available as Matlab code:

Main function: HeadPoseEstim_CMTech.m
input:         npy file name with depth information from Kinect 2
output:        pitch, yaw, roll angles

=======================
if found our script helpful, please cite it as:

Dmytro Derkach, Adria Ruiz and Federico M. Sukno 
“Head Pose Estimation Based on 3-D Facial Landmarks Localization and Regression” 
12th IEEE Conference on Automatic Face and Gesture Recognition 2017

@inproceedings{derkach2017head,
  title={Head Pose Estimation Based on 3-D Facial Landmarks Localization and Regression},
  author={Derkach, Dmytro and Ruiz, Adria and Sukno, Federico M},
  booktitle={Automatic Face \& Gesture Recognition (FG 2017), 2017 12th IEEE International Conference on},
  pages={820--827},
  year={2017},
  organization={IEEE}
}
You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.