数字媒体技术系邀请学术报告信息

2015年06月10日 09:51  点击:[]

通知日期(月) 通知日期(日)

     报告一:


报告人: 天津大学冯伟副教授 

报告时间:2015年6月9日(周二)下午13:30 
报告地点:软件学院教学楼A401录播室。  
报告对象:相关专业教师、研究生和本科生,本科生带好讲座卡,或来教学楼A113领取讲座卡。  
报告题目:Detecting Spiral Symmetry Structure from Single Image via Matched Feature Triplets

中文题目:基于匹配三元组的单幅图像广义螺旋对称结构检测

报告摘要:

Recently, radial symmetry detection becomes an essential topic in computer vision due to its significance in understanding image content. This paper presents a major generalization to the problem and studies nonspecific single image spiral symmetry structure detection. Compared to the classical radial symmetry, which is just a special case in the studied spiral symmetry model, spiral symmetry structure detection is more challenging and needs multiple parameters estimation and complex structure reconstruction. For this new problem, we propose a fast and effective voting solution driven by the matched feature triplets (MFTs). Our approach is able to reliably determine the dominant spiral centroid, the spiral growing direction, the common growth rate, and the evident initial radii set of a spiral symmetry structure from single image. Extensive experiments on both man-made and natural scenes validate the effectiveness and superiority of the proposed approach.    


报告人简介:Wei Feng received the B.S. and M.Phil. degrees in Computer Science from Northwestern Polytechnical University, China, in 2000 and 2003 respectively, and the Ph.D. degree in Computer Science from City University of Hong Kong in 2008. From 2008 to 2010, he worked as research fellow at the Chinese University of Hong Kong and City University of Hong Kong, respectively. He is an associate professor in School of Computer Science and Technology and the director of Computer Vision and Media Computing Center of Tianjin University. His major research interest is media computing, specifically including general Markov Random Fields modeling, discrete/continuous energy minimization, image segmentation, semi-supervised clustering, structural authentication, and generic pattern recognition. He has published more than 50 academic papers, including TPAMI, IJCV, TIP, PR, CVPR and ICCV. He got the support of the Program for New Century Excellent Talents in University, China, in 2011.

 

 

 

     报告二:

 

报告人: 天津大学万亮副教授 

报告时间:2015年6月9日(周二)下午14:20 
报告地点:软件学院教学楼A401录播室。  
报告对象:相关专业教师、研究生和本科生,本科生带好讲座卡,或来教学楼A113领取讲座卡。  
报告题目:360度全景图像处理



报告摘要:

 

360度全景图将观测点四周的景观记录在一张图像上,提供远超普通镜头以及人眼的观察视角。得益于数字图像拼接技术的革新、球面全景相机的不断发展、智能手机的普及,全景图的获取已经越来越容易。360度全景图已被大量用于电脑游戏、电影特效、虚拟现实等应用中,极大地提高了三维场景渲染的真实感。我们将介绍近年来本课题组在全景图像处理上的研究进展,重点包括基于全景图的实时虚拟浏览以及面向全景图的球面特征提取。在深入分析全景图的几何特点后,提出基于球面域的视点合成技术以及快速鲁棒的球面特征描述符,与现有方法的实验比较证明了所提技术的有效性和高效性。

 

报告人简介:

万亮,副教授,天津大学软件学院。她于2007年获得香港中文大学计算机科学与技术系的哲学博士学位,2007年至2011年于香港城市大学电子工程系从事博士后工作。2011年加入天津大学软件学院,2012年被评为天津大学第一届北洋青年骨干教师。主要研究兴趣为计算机图形图像处理领域,具体涉及360度视角全景图像处理、基于图像的渲染、三维模型处理等方向。

上一条:国防科技大学海洋信息与工程研究院来院访问 下一条:立命馆大学信息理工学院研究介绍

关闭