新闻中心
学术预告-新西兰奥克兰理工大学Reinhard教授学术讲座
作者:宫相栋        发布时间:2018-09-03        点击数:


报告题目:Large-scale 3D Roadside Modelling with Road Geometry Analysis: Digital Roads New Zealand

报告日期及时间:2018910日 下午4:00-5:30

报告地点: 振声苑S104

报告人: Prof. Reinhard Klette

报告人单位:新西兰奥克兰理工大学

报告人简介:Prof. Reinhard Klette

Reinhard Klette教授现任新西兰皇家科学院院士,新西兰奥克兰理工大学教授,机器与视觉研究中心主任。Klette教授分别于1973年和1978年获得德国耶拿大学数学硕士和博士学位,并于1982年获得德国耶拿大学计算机科学博士学位,曾任德国科学院、柏林技术大学,以及新西兰奥克兰大学教授。Reinhard Klette教授在IEEE T IPIEEE T ITSPattern RecognitionCVIUIEEE T Vehicular Technology等国际期刊与CVPRICCVIROSAI会议发表相关学术论文100余篇。2003年,与美国马里兰大学Azriel Rosenfeld教授合作编著首部综合性专著《数字图像几何算法》(Digital Geometry Morgan Kaufmann出版社)。1995年至今,多次应邀作为重要国际学术会议的主讲嘉宾。20114月至201310月任JCET(控制工程和技术)期刊创刊主编。2001年至2008年任IEEE PAMI副主编(电子工程领域引用率最高的期刊)。欧洲计算机图形和模式分析委员会终身荣誉会员,环太平洋图像和视频技术研讨委员会委员。研究方向包括基于视觉的驾驶员辅助驾驶、计算机视觉与道路安全、人的姿态理解、艺术与计算机视觉和视频数据的语义分割等。
报告摘要:

Latest developments in camera technology and computer vision, as well as in computer and communication technologies, contribute to improving safety on roads by the development of new key technologies, such as autonomous driving or driver-assistance systems. These new technologies need to be tested extensively and purposefully, and supported by environment or infrastructure models or integrated sensors. The paper reports about a project ``Digital Roads New Zealand”, undertaken by DLR Berlin (an institute of the German Aerospace Centre), AUT, and N3T, a company at Whangarei. Novel sensor technologies, including stereo vision and odometry, have been used for recording, modelling and analysing a large test site. It is demonstrated how those data can be used for detecting changes in road geometry, such as various forms of road surface distress. An important novelty of the shown solution is the scale of the project (i.e. size of the digitised area using car-mounted sensors) together with the achieved very high accuracy in road-geometry analysis. - This talk is joint work with Ines Ernst, Hongmou Zhang, and Sergey Zuev at DLR, Martin Knoche at N3T, and Amita Dhiman and Hsiang-Jen Chien at AUT.