Generation and Visualization of Large Scale Self Consistent 3D Reconstructions from Robotic Surveys
Dr. Matthew Johnson-Roberson (KTH Royal Institute of Technology)
CSIRO ICTDATE: 2010-08-24
TIME: 14:00:00 - 15:00:00
LOCATION: Seminar Room S206, CSIRO Mathematics, Informatics and Statistics, Building 108, ANU
CONTACT: JavaScript must be enabled to display this email address.
ABSTRACT:
Robust, scalable algorithms for mapping and localization support the successful deployment of robots in real-world applications. In many cases these platforms are now capable of delivering vast amounts of sensor data from large scale, potentially unstructured environments. This data may be difficult to interpret by end-users without further processing and suitable visualization tools. This talk will discuss a robust, automated system for large-scale 3D reconstruction and visualization that takes stereo or mono imagery and SLAM-based poses to deliver detailed 3D models of the seafloor in the form of textured polygonal meshes. Our system allows the user to quickly zoom down to the cm level and out to the km level while interacting with the reconstruction.
BIO:
Dr. Matthew Johnson-Roberson is a postdoctoral researcher at KTH Royal Institute of Technology. He works on issues of perception and sensor processing for robotic platforms. He holds a B.S. in Computer Science from Carnegie Mellon University and a Ph.D. in Robotics from the University of Sydney. He is interested in computer vision and machine learning, specifically their applications to real world problems in challenging unstructured environments.
