讲 座

主 题：活动视频中的对象抽取与重构（内容）
主讲人：厉泽年教授
        （School of Computing Science，Simon Fraser University，Vancouver, BC, Canada）
时 间：2004年12月28日下午14：50
地 点：逸夫楼302室

Abstract
A new method of video object extraction is proposed to accurately obtain the object of interest from actively acquired videos. A passive/static camera simply records all objects passing by in front of it. The video objects thus captured are often by chance (at random). In contrast, the proposed active video object extraction (AVOE) paradigm assumes that the object of interest is being actively tracked by a camera moving in 3D and classifies the possible motions of the camera that result in the 2D motion patterns as recovered from the 2D image sequence. Consequently, the AVOE method is able to extract the single object of interest from the active video. We formalize the AVOE process using notions from Gestalt psychology. We define a new Gestalt operator called "foveation" which acts as a bridge between 2D Gestalt groupings and 3D object perception.

Using the recovered motion fields between successive frames of the video, we propose a linear programming based object extraction algorithm that takes into account the strength and orientation of potential edges that belong to the object of interest as well as the recovered motion vectors. Since an active video sequence naturally contains multiple views of the object of interest, a logical step forward from 2D object extraction is the reconstruction of the 3D object of interest from multiple views. In this talk, we describe the design and implementation of an active video object extraction and reconstruction system.

Biography:
Ze-Nian Li is a Professor in the School of Computing Science at Simon Fraser University in Vancouver, Canada. He was the Director of the School of Computing Science from 2001 to 2004. Dr. Li received his undergraduate education in Electrical Engineering from the University of Science and Technology of China, and M.Sc. and Ph.D. degrees in Computer Sciences from the University of Wisconsin-Madison. Earlier in his career he was an electronic engineer in charge of design of digital and analogical systems. His current research interests include multimedia, computer vision, pattern recognition, image processing, and artificial intelligence. Dr. Li is the Director of Vision and Media Lab at Simon Fraser University. He has published over 80 refereed papers in journals and conference proceedings. He is the co-author of the book "Fundamentals of Multimedia" published by Prentice Hall in 2004.

简报

    加拿大Simon Fraser University 厉泽年教授到我校进行访问并为我校师生做学术报告。

    2004年12月28日，加拿大Simon Fraser 大学计算机系主任厉泽年教授应中山大学信息科学与技术学院软件研究所的邀请，到中山大学进行访问并在逸夫楼302多媒体课室为我校师生做关于“活动视频中的对象抽取与重构”的学术报告。
    上午10时30分至下午2时45分，厉泽年教授先后到中山大学软件研究所、电子与通信系及信科院进行访问，信科院院长黄继武教授，软件研究所所长李磊教授，姜云飞教授，电子系沈伟教授就目前双方感兴趣的专业问题及热点问题与厉教授进行深入的交流。厉教授还参观了软件所实验室，电子系实验室及通信实验室，同时给予了较高的评价。
    下午3时，厉泽年教授在我校逸夫楼302多媒体课室为我校（特别是信息科学与技术学院及软件学院）师生做学术报告。参加报告的师生济济一堂，聆听了关于“活动视频中的对象抽取与重构”的学术报告，受益匪浅。报告结束后师生提出相关问题与厉教授讨论和交流。本次报告十分精彩，同学们最后报以热烈的掌声。通过这次报告，使大家更多地了解到关于活动视频方面的新信息，新动态。
    综述：本次访问及讲座达到软件研究所原计划的效果和水平。

报告人：软件研究所 罗洁丽
2004年12月28日