Andrew Davison
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife


I hold the position of Reader in Robot Vision at the Department of Computing, Imperial College London, and lead the Robot Vision Research Group. I am working in computer vision and robotics: specifically my main research over the past few years has been on SLAM (Simultaneous Localisation and Mapping) using vision, with a particular emphasis on methods that work in real-time with a single camera which can be classed as Real-Time Structure from Motion, or as I would rather call it Single Camera SLAM or MonoSLAM (vision-based, monocular, bearing-only SLAM, in full 3D and without inertial sensing). This is technology that could provide cheap real-time localisation for domestic robots, humanoid robots, wearable sensors, game interfaces or other devices. This work derives from my early research at the University of Oxford where I developed one of the very first real-time SLAM systems for robot navigation, and the first using vision as its primary sensor (ECCV 1998).

Currently my main interests are in improving the performance in terms of dynamics, scale and detail level of real-time visual localisation and mapping. Imperial College Robotics; Imperial College Computer Vision: please contact me if you are interested in coming to Imperial for PhD studies or post-doctoral research as I am always looking for excellent new team members. Post-doctoral researchers with an interest in the department, please have a look at the recently announced Imperial College Junior Research Fellowships or the Newton International Fellowships.


flag Monocular SLAM and Real-Time Scene Perception
as author at  British Machine Vision Conference (BMVC), Surrey 2012,