学术报告:Information Processing for Live Photo Mosaic with a Group of Wireless Image Sensors

报告题目:Information Processing for Live Photo Mosaic with a Group of Wireless Image Sensors

报告人:李夫路 博士

时 间: 2016年11月29日(周二)下午3:00-4:30

地 点: 北京大学计算机科学技术研究所1层106会议室

摘要: Photo tourism is a platform that allows users to transform unstructured online digital photos into a 3D experience. Nowadays, image sensors are being extensively used to allow images to be taken automatically and remotely, which facilitates the opportunity for live update of photo mosaics. In this paper, we present a novel framework for live photo mosaic with a group of wireless image sensor nodes, where the image data aggregation is accomplished in an efficient and distributed way. Essentially, we propose to conduct clustering and data compression at wireless image sensor network level while conserving the completeness of the feature point information for reconstruction. Toward the realization of the whole system, we have built image sensor prototypes with commodity cameras and we validated our approach by indepth analysis, extensive simulations and field experiments.

报告人简介: 李夫路博士毕业于美国麻省理工学院(MIT),现为清华大学、电子科技大学兼职教授,先后在MIT Media Lab获硕士和博士学位,研究领域包括无线通信、信息编码、群体计算、数据压缩、大数据存储、高端数据库、贝叶斯网络、节能路由算法、复杂系统时间序列的实时智能诊断等,独立发明的互联网数据包快速分类哈希缓存技术被微软、IBM、Intel、思科等全球主要高科技公司的技术发明专利引用152次,在国际顶级会议(ACM/IEEE IPSN)上发表论文(论文接受率17%),论文/专利他引次数超过100次的有六篇,总共论文他引次数超过1200次,曾获IEEE 无线通信年会实践创新论文奖(For Excellence in Applied Research)。

[关闭]
版权所有 © 2007 北京大学计算机科学技术研究所