学术报告：Semantic Segmentation of Street View Images Using Graph Matching and Point Clouds
来源：betway必威西汉姆联官网 时间：2017-04-21 浏览：
报告题目：
Semantic Segmentation of Street View Images Using Graph Matching and Point Clouds
报告简介：
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. Through integrating several additional terms, A multimedia approach to visualize and interact with large scale mobile LiDAR datathe 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.
主讲人简介：
 |
|
王瑞胜，博士，加拿大卡尔加里大学地球空间信息工程系终身教授，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、激光和图像中物体的提取识别及三维重建、航空遥感图像和探测数据的智能处理等。本科毕业于必威betway官网入口摄影测量与遥感专业，获得加拿大新不伦瑞克大学地球空间信息工程专业硕士学位、加拿大麦吉尔大学计算机工程专业的博士学位。博士期间，获Benedek研究生奖、Vadasz学者奖、麦吉尔大学工程博士奖、加拿大国家自然科学基金会博士奖学金。
曾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。
2012年至今在卡尔加里大学工作，2014、2016年先后两次获得Google Research Award，并被Elsevier和ISPRS Journal of Photogrammetry and Remote Sensing评为优秀审稿人。
|
|
时间：2017年4月24日（周一）下午15:00
地点：遥感betway必威西汉姆联官网附3-202报告厅
