6533b830fe1ef96bd1296f91
RESEARCH PRODUCT
Head Pose Estimation for Sign Language Video
Jorma LaaksonenMarcos LuzardoMatti KarppaTommi Jantunensubject
business.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONSign language3D pose estimationMotion captureData setSupport vector machineMinimum bounding boxFace (geometry)Computer visionArtificial intelligencebusinessPosedescription
We address the problem of estimating three head pose angles in sign language video using the Pointing04 data set as training data. The proposed model employs facial landmark points and Support Vector Regression learned from the training set to identify yaw and pitch angles independently. A simple geometric approach is used for the roll angle. As a novel development, we propose to use the detected skin tone areas within the face bounding box as additional features for head pose estimation. The accuracy level of the estimators we obtain compares favorably with published results on the same data, but the smaller number of pose angles in our setup may explain some of the observed advantage.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2013-01-01 |