文献翻译Mean Shift.docx

英文翻译 分　 院 　 　 专 业 　 届 别 学 号 姓 名 指导教师 2009 年 05 月 10日 文献翻译一：原文 NON-RIGID OBJECT LOCALIZATION FROM COLOR MODEL USING MEAN SHIFT Ga?l Jaffré and Alain Crouzil. Non-rigid object localization from color model using mean shift[D]. IEEE. International Conference on Image Processing(ICIP 2003) Ga?l Jaffré Alain Crouzil Institut de Recherche en Informatique de Toulouse Université Paul Sabatier - 118 route de Narbonne - 31062 Toulouse Cedex 4 - France {jaffre, crouzil}@irit.fr ABSTRACT This paper deals with non-rigid object localization in an image, from object colors. Our method allows detection in an image of all the objects which correspond to a color model, without a priori information about their number. Our approach consists in creating a binary image, which represents the repartition of the most probable pixels to be part of the object. Considering this image as a cluster in , the object localization is done by finding all the cluster modes. This search is carried out by applying a statistical method: the mean shift procedure. To illustrate our approach, we use sport images, from which we try to detect all the players. INTRODUCTION Our framework is sport image sequence analysis, especially player tracking. In this study, our topic search is non-rigid object localization in an image, to automatically initialize tracking procedures. This problem is often encountered in tracking applications where search is local (tracking with snakes, mean shift tracking, …). The search being done in the neighborhood of the object position in the previous frame, initialization is needed for the first frame. Due to many difficulties, it is usually a manual initialization [1, 2]. Our problem presents two main difficulties : the non-rigid and the 3D aspects of t