ICS, CNE, HCR Doctoral Seminar on "Visual odometry with RGB-D camera"
Abstract: Six degrees of freedom odometry estimation from visual data, i.e. estimation of camera’s position and orientation from images, is one of the most active research area in robotic vision. In recent years, the availability of lightweight RGB-D sensors such as Asus Xtion raised the popularity of visual odometry estimation from depth information. To simplify the problem formulation, most state-of-the-art visual odometry methods assume a static environment. However, dynamic objects, such as human, exist in many real life environments, which cannot be handled by many state-of-the-art methods. This talk presents an efficient and accurate visual odmetry method developed in HCR, which can also handle dynamic objects in the environment. Furthermore, the integration to a SLAM (Simultaneous Localization and Mapping) system will be also presented.
Bio: Shile Li received his B.Sc. and M.Sc degree in Electrical and Computer Engineering from TUM, Germany, in 2012 and 2015, respectively. He is currently pursuing the Ph.D. degree in Human-centered Assistive Robotics Lab at TUM. His research interests include object pose tracking, visual odometry and hand pose estimation using RGB-D camera.
16 January 2019, 16:30h, ICS Karlstraße 45, 6. Floor, room 6009
For more info please visit: http://web.ics.ei.tum.de/~ehrlich/ICS_seminar/index.htm