Head Detection and Localization from Sparse 3D Data

Head detection is an important, but difficult task, if no restrictions such as static illumination, frontal face appearance or uniform background can be assumed. We present a system that is able to perform head detection under very general conditions by employing a 3D measurement system namely a structured light distance measurement. An algorithm of head detection from sparse 3D data (19×19 data points) is developed that reconstructs a 3D surface over the image plane and detects head hypotheses of ellipsoidal shape. We demonstrate that detection and rough localization is possible in up to 90% of the images.

[1]  Joaquim Salvi,et al.  An overview of the advantages and constraints of coded pattern projection techniques for autonomous navigation , 1997, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97.

[2]  Zhengyou Zhang,et al.  Flexible camera calibration by viewing a plane from unknown orientations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Liming Zhang,et al.  A new head detection method based on the region shield segmentation in complex background , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).

[4]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[5]  Giovanna Sansoni,et al.  Calibration and performance evaluation of a 3-D imaging sensor based on the projection of structured light , 2000, IEEE Trans. Instrum. Meas..

[6]  Kazuhiko Takahashi,et al.  Real-time, 3D estimation of human body postures from trinocular images , 1999, Proceedings IEEE International Workshop on Modelling People. MPeople'99.

[7]  Ales Leonardis,et al.  Grasping arbitrarily shaped 3-D objects from a pile , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[8]  Allen M. Waxman,et al.  Structured light patterns for robot mobility , 1988, IEEE J. Robotics Autom..

[9]  Horst Bischof,et al.  Tracking structured light pattern , 2001, SPIE Optics East.

[10]  Juha Röning,et al.  Intelligent Robots and Computer Vision XXIII: Algorithms, Techniques, and Active Vision , 1992 .

[11]  Ray A. Jarvis,et al.  A Perspective on Range Finding Techniques for Computer Vision , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Janne Heikkilä,et al.  A four-step camera calibration procedure with implicit image correction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Tomaso A. Poggio,et al.  A Trainable System for Object Detection , 2000, International Journal of Computer Vision.

[14]  G.C. Stockman,et al.  Sensing and recognition of rigid objects using structured light , 1988, IEEE Control Systems Magazine.

[15]  Yan Guo,et al.  Tracking of Moving Heads in Cluttered Scenes from Stereo Vision , 2001, RobVis.

[16]  Andrew Blake,et al.  Trinocular Active Range-Sensing , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  A. Giralt,et al.  Head detection inside vehicles with a modified SVM for safer airbags , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[18]  D. Gavrila,et al.  3-D model-based tracking of human upper body movement: a multi-view approach , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[19]  Nikolaos Grammalidis,et al.  Head detection and tracking by 2-D and 3-D ellipsoid fitting , 2000, Proceedings Computer Graphics International 2000.