This talk presents a novel scene parsing approach via structure transferring on both images and point clouds. Unlike traditional methods that extract joint features from images and point clouds, we introduce a new framework which processes images and point clouds in separate pipelines and combine them in the inference step. We also propose a structure transfer scheme by finding maximal similar parts across scenes, which is realized via graph matching with a new model. The transferred structures, as well as the information from point clouds, are integrated in a new energy function to enhance the inference performance. Though integrating several additional terms, the energy function does not introduce any higher-order potentials, remaining a locally connected pairwise Markov Random Field (MRF), which can be efficiently optimized. We evaluate the approach on several challenging datasets, achieving promising performance. 

  Speaker Bio: 王瑞胜博士是加拿大卡尔加里大学智能空间信息研究室主任。主要研究方向为大规模三维城市建模中的航空和移动激光技术的整合、激光和图像中智能特征的提取识别及三维重建技术、航空图像和探测数据的智能处理等。他毕业于武汉大学摄影测量与遥感专业，获加拿大新不伦瑞克大学地理信息工程专业硕士学位及加拿大麦吉尔大学计算机工程专业的博士学位。王博士在美国芝加哥诺基亚公司位置与商务部任研究员（2008-2012），主要研究方向是基于移动激光的下一代地图制作和导航技术，并先后八次获得重大创新发明奖。于2012年加入卡尔加里大学，获得两次谷歌研究奖（Google Research Award，2016， 2014），并被Elsevier和ISPRS Journal of Photogrammetry and Remote Sensing评为优秀审稿人。目前任国际摄影测量与遥感学会激光点云数据处理工作组学术秘书和国际摄影测量与遥感期刊的顾问编委会成员 (ISPRS Journal).  

报告时间:2016年4月28日下午2:30 

报告地点:2321会议室 

主  持  人: 苏奋振研究员