Seminario: Lunes 8 de enero a las 12:00 en el Seminario del DIIS (Ada Byron)
Speaker: Guillermo Gallego (University of Zurich)
Title: Camera autocalibration and event-based vision for SLAM
Abstract of the talk:
The recovery of the calibration parameters of the cameras is paramount in 3D reconstruction since it provides metric information about the observed scene, e.g., measures of angles and ratios of distances. Camera autocalibration enables the estimation of the camera parameters without using a calibration device (e.g., checkerboard), by enforcing simple constraints on the camera parameters, such as constant intrinsic parameters in multiple images, known principal point, known pixel shape, etc. In this talk I will present some camera autocalibration methods developed at the Grupo de Tratamiento de Imagenes of the Universidad Politecnica de Madrid.
I will also take this opportunity to present some recent advances carried out at the Robotics and Perception Group of Prof. Davide Scaramuzza (University of Zurich) on Visual Odometry with event cameras, which are biologically inspired sensors that present a new paradigm on the way that visual information is acquired and processed.
Event-based vision for SLAM:
Guillermo Gallego received the Ph.D. in Electrical and Computer Engineering from Georgia Institute of Technology, USA, in 2011. He was a recipient of the Fulbright Scholarship to pursue graduate studies in 2005. From 2011 to 2014, he was a Marie Curie Experienced Researcher with Universidad Politecnica de Madrid, Spain. Since 2014 he is a post-doctoral researcher with the Robotics and Perception Group, University of Zurich, Switzerland. His research interests fall within the areas of computer vision, signal processing, robotics, geometry, optimization, and ocean engineering.