3D Face tracking and gaze estimation using a monocular camera

Estimating a user’s gaze direction, one of the main novel user interaction technologies, will eventually be used for numerous applications where current methods are becoming less effective. In this paper, a new method is presented for estimating the gaze direction using Canonical Correlation Analysis (CCA), which finds a linear relationship between two datasets defining the face pose and the corresponding facial appearance changes. Afterwards, iris tracking is performed by blob detection using a 4-connected component labeling algorithm. Finally, a gaze vector is calculated based on gathered eye properties. Results obtained from datasets and real-time input confirm the robustness of this method

[1]  Jian-Gang Wang,et al.  Eye gaze estimation from a single image of one eye , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[2]  Fadi Dornaika,et al.  Real time 3D face and facial feature tracking , 2007, Journal of Real-Time Image Processing.

[3]  Heiko Neumann,et al.  A comprehensive head pose and gaze database , 2007 .

[4]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[5]  Takahiro Ishikawa,et al.  Passive driver gaze tracking with active appearance models , 2004 .

[6]  Henk Spekreijse,et al.  UvA-DARE ( Digital Academic Repository ) Near infrared light absorption in the human eye media , 2022 .

[7]  Michael R. Lyu,et al.  Automatic 3D Face Modeling Using 2D Active Appearance Models , 2005 .

[8]  Zhiwei Zhu,et al.  Novel Eye Gaze Tracking Techniques Under Natural Head Movement , 2007, IEEE Transactions on Biomedical Engineering.

[9]  Leopoldo Altamirano Robles,et al.  Interpreting Face Images by Fitting a Fast Illumination-Based 3D Active Appearance Model , 2009, MIRAGE.

[10]  Zhiwei Zhu,et al.  Robust real-time eye detection and tracking under variable lighting conditions and various face orientations , 2005, Comput. Vis. Image Underst..

[11]  Jörgen Ahlberg,et al.  CANDIDE-3 - An Updated Parameterised Face , 2001 .

[12]  Vladimir Vezhnevets,et al.  Robust and Accurate Eye Contour Extraction , 2003 .

[13]  Stefanos Kollias,et al.  A natural head pose and eye gaze dataset , 2009, AFFINE '09.

[14]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[15]  David S. Young,et al.  Specialised Hough Transform and Active Contour Methods for Real-Time Eye Tracking , 2012 .

[16]  Fred Nicolls,et al.  Locating Facial Features with an Extended Active Shape Model , 2008, ECCV.

[17]  Alois Knoll,et al.  Real-Time 3D Face Tracking with Mutual Information and Active Contours , 2007, ISVC.

[18]  Alexander Zelinsky,et al.  Behavior recognition based on head pose and gaze direction measurement , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[19]  Franck Davoine,et al.  A linear estimation method for 3D pose and facial animation tracking , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  David Weenink,et al.  CANONICAL CORRELATION ANALYSIS , 2003 .

[21]  Alexander Zelinsky,et al.  3-D facial pose and gaze point estimation using a robust real-time tracking paradigm , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[22]  Sangmin Oh,et al.  A Note on Singular Value Decomposition ∗ , 2005 .