Maximum correntropy criterion based 3D head tracking with commodity depth camera

Shaoguo Liu,Haibo Wang,Ying Wang,Jixia Zhang,Chunhong Pan

ICIP（2013）

Cited 1|Views31

No score

Abstract

3D head tracking becomes easier with the depth image from Microsoft Kinect. However, the noise from face occlusion and illumination still affects the tracking quality. In this paper, we introduce the robust Maximum Correntropy Criterion (MCC) to the problem of 3D head tracking, to tackle these noises. Fortunately, MCC can handle arbitrarily distributed noises. To solve the MCC based cost function, we develop an effective two-stage optimization scheme with the half-quadric technology. A head tracking system that uses Miscrosoft Kinect is also developed based on the MCC formulation. The system is fully automatic and online, without need of offline training. Experimental results show that the system is very robust against partial occlusion, large motion and sudden illumination variations.

Translated text

Key words

optimisation,offline training,arbitrarily distributed noise handling,half-quadric technology,face occlusion noise,robust maximum correntropy criterion,commodity depth camera,pose estimation,two-stage optimization scheme,mcc,3d head pose estimation,maximum entropy methods,object tracking,cameras,motion variation robustness,3d head tracking,3d head tracking system,illumination variation robustness,two-stage optimization,kinect,microsoft kinect,depth image,partial-occlusion variation robustness,mcc based cost function

AI Read Science

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Chat Paper

Summary is being generated by the instructions you defined