报告题目:Towards Self-driving Cars: Test Fields, Visual Odometry, and Road-surface Analysis
报 告 人:Reinhard Klette,新西兰皇家科学院院士,新西兰奥克兰理工大学 教授
报告时间:2019年6月26日(星期三)下午16:00~17:00
报告地点:12教703
报告内容:
In the context of test field studies, the talk informs about computer-vision based components towards self-driving cars. Visual odometry supports exact geo-localization of vehicles on the road, and in particular also accurate 3-dimensional roadside reconstruction, thus improving GPS/IMU-only based approaches.
Different camera configurations contribute to options for sensor configurations in self-driving cars. The talk discusses results for visual odometry for evaluating different camera configurations. It is also demonstrating how visual odometry provides important information for improved road-surface distress analysis.
报告人简介:Reinhard Klette,现任新西兰皇家科学院院士,新西兰奥克兰理工大学教授,机器人与视觉中心主任。Reinhard Klette教授在IEEE Trans., CVPR, ICCV, IROS等国际顶级期刊和会议上发表相关学术论文100余篇。2003年,与美国马里兰大学Azriel教授合作编著首部综合性专著《数字图像几何算法》。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,2001-2008担任IEEE Transactions on Pattern Analysis and Machine Intelligence副主编。近期主要研究方向为基于视觉的辅助驾驶、计算机视觉和道路安全、人的姿态理解等。