报告题目：Synthetic Aperture Imaging Using Camera Array

报 告 人：裴 炤

报告时间：2013年11月27日 下午15:00-16:00

报告地点：计算机科学学院报告厅

报告人简介：Dr. Pei received his B.Eng. degree in Computer Science and Technology, M.Sc. degree in Computer Software and Theory and Ph.D. degree in Computer Science and Technology from Northwestern Polytechnical University, Xian, China, in 2005, 2008 and 2013, respectively. From Sept. 2010 to Oct. 2011 he was a visiting Ph.D. student in the Department of Computing Science, The University of Alberta, Canada. Since Aug.2013, He has been a Lecturer in the School of Computer Science, Shaanxi Normal University, Xian, China. His research interests include Computer Vision, Image Processing and Pattern Recognition, Multimedia Processing. He has 2 papers published on the international journal Pattern Recognition in pattern recognition and computer vision field. More information can be found in his homepagehttps://sites.google.com/site/zpeics/.

报告内容简介：Synthetic aperture imaging is a technique that projects images of a scene from different views onto a virtual focal plane to mimic a camera with a large virtual convex lens. It can easily handle the occlusion problem in the field of computer vision by “seeing through” occluders that makes synthetic aperture imaging a powerful method for video surveillance. Unfortunately, the resulting image is still blurry because it combines information not only from the region of interest but also from the occluding regions. Removing the blurriness of synthetic aperture images has become a challenging task for many computer vision applications. This talk will introduce some novel methods to improve the image quality of synthetic aperture imaging using background subtraction, energy minimization etc. The experimental results show that the proposed methods outperforms the traditional synthetic aperture imaging method as well as its improved versions, which simply dim and blur occluders in the resulting image.