最新消息

2012年7月2日学术报告:Simultaneously Fitting and Segmenting Multiple-Structure Data with Outliers,厦门大学闽江学者王菡子教授


添加时间:2012-06-28 17:54:55



时间与地点:7月2日(周一)下午2点,中心教学楼1003会议室
报告人:王菡子教授(厦门大学闽江学者教授)
报告题目:Simultaneously Fitting and Segmenting Multiple-Structure Data with Outliers
Abstract: Robust statistical methods play a vital role in many activities in computer vision research. When engaged in the applications in a computer vision context, it is important to recognize that it is almost unavoidable that data are contaminated by noise and outliers (due to faulty feature extraction, segmentation errors, etc) and it is also likely that the data will include multiple structures. Thus, it has been widely acknowledged that all algorithms in computer vision should be robust for accurate estimation. To fit a model to noisy data (with a large number of outliers and multiple structures) is still a major and challenging task within the computer vision communities. In this talk, I will introduce some of my recent work on robust statistics and its various applications, including line fitting, circle fitting, range image segmentation, homography estimation and two-view based motion segmentation, etc.

王菡子教授,厦门大学“闽江学者”特聘教授,澳大利亚Adelaide大学兼职教授(Adjunct Professor)厦门大学模式分析与机器智能研究中心主任; 1996和1999年分别获四川大学学士与硕士学位。2004年获澳大利亚MONASH大学博士学位,并荣获Douglas Lampard最佳博士论文奖。 2004至2006年在澳大利亚MONASH大学电子计算机系统工程系任Research Fellow。2006至2008年在美国JOHNS HOPKINS大学计算机科学系任Postdoctoral Fellow和Assistant Research Scientist)。2008至2010年在澳大利亚Adelaide大学计算机学院任职高级研究员(Senior Research Fellow)。2010年入选厦门大学“闽江学者”特聘教授主要研究方向:计算机视觉和模式识别,图像和视频处理,视频跟踪与监控,三维重构等。 在国内外重要学术期刊和国际学术会议上已发表论文50多篇,其中,多篇发表在国际顶级期刊IEEE TPAMI、IJCV、IEEE TMI和国际权威期刊IEEE TCSVT, PR, PR Letters,Neurocomputing上,以及国际顶尖会议ICCV,ECCV,CVPR,NIPS,MICCAI上。被SCI收录20多篇,EI收录30多篇。现为IEEE高级会员(Senior Member),担任国际权威SCI期刊《IEEE Transactions on Circuits and Systems for Video Technology》副主编(Associate Editor)和国际重要SCI期刊《Pattern Recognition Letters》特邀编委(Guest Editor-2009年)。
 


作者:杨蛟龙