Improvement of a Person Labelling Method Using Extracted Knowledge on Costume

This paper presents a novel approach for automatic person labelling in video sequences using costumes. The person recognition is carried out by extracting the costumes of all the persons who appear in the video. Then, their reappearance in subsequent frames is performed by searching the reappearance of their costume. Our contribution in this paper is a new approach for costume detection, without face detection, that allows the localization of costumes even if persons are not facing the camera. Actually face detection is also used because it presents a very accurate heuristic for costume detection, but in addition in each shot mean shift costume localization is carried out with the most relevant costume when face detection fails. Results are presented with TV broadcasts.

[1]  Charay Lerdsudwichai,et al.  Algorithm for multiple faces tracking , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[2]  Omar Javed,et al.  University of Central Florida at TRECVID 2004 , 2003, TRECVID.

[3]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[4]  Arie Hordijk,et al.  Time-discretization for controlled Markov processes. I. General approximation results , 1996, Kybernetika (Praha).

[5]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  A Gordon,et al.  Classification, 2nd Edition , 1999 .

[7]  Seong-Whan Lee,et al.  Multiple pedestrian detection and tracking based on weighted temporal texture features , 2004, ICPR 2004.

[8]  Steve McLaughlin,et al.  Comparative study of textural analysis techniques to characterise tissue from intravascular ultrasound , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[9]  Earl E. Swartzlander,et al.  Introduction to Mathematical Techniques in Pattern Recognition , 1973 .

[10]  G. Jaffré,et al.  Costume: a new feature for automatic video content indexing , 2004 .

[11]  A. Broggi,et al.  Pedestrian localization and tracking system with Kalman filtering , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[12]  Alain Crouzil,et al.  Non-rigid object localization from color model using mean shift , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[13]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[14]  Itheri Yahiaoui.  Construction automatique de résumés vidéos , 2003 .

[15]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[16]  Frank-Michael Nack,et al.  AUTEUR : the application of video semantics and theme representation for automated film editing , 1996 .

[17]  Narendra Ahuja,et al.  Detecting Faces in Images: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  David G. Stork,et al.  Pattern Classification , 1973 .

[19]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[20]  Neil A. Thacker,et al.  The Bhattacharyya metric as an absolute similarity measure for frequency coded data , 1998, Kybernetika.