PCV 19 Keynote abstracts
Title: Industry insights for photogrammetry application
Speaker: Christoph Strecha
Abstract: Photogrammetry as discipline did undergo a rapid development in the years 1998-2005. Industry application with large manual intervention have been widely switched towards fully or highly automated industry workflows. On top of this Photogrammetry is widely used by people, which are not aware of the underlying technology and that care more about how this technology brings value to them. In this talk I would like to touch on some of those valuable results and usage examples of Photogrammetry today. I will present problems in Agriculture, Emergency response, crime scene analysis, inspection, Oil and gas and asset management today that go beyond Photogrammetry and would allow an even larger adoption of this technology.
Title: Realtime Visual SLAM for Autonomous Systems
Speaker: Daniel Cremers
Abstract: The reconstruction of the 3D world from moving cameras has seen enormous progress over the last couple of years. Already in the 2000s, researchers have pioneered algorithms which can reconstruct camera motion and sparse feature-points in real-time. In my talk, I will introduce direct methods for camera tracking and 3D reconstruction which do not require feature point estimation, which exploit all available input data and which recover dense or semi-dense geometry rather than sparse point clouds. I will present recentdevelopments on Simultaneous Localization and Mapping (SLAM) using monocular and stereo cameras, inertial sensors and deep neural networks.