Research

The task of estimating sensor motion from measurements of a continuously expanding set of self-mapped features is known as Simultaneous Localisation and Mapping (SLAM). It has recently been shown that SLAM techniques can be successfully applied to estimate the ego-motion of a single agile camera in real-time by building a sparse map of visual features on the fly. My work is focused on applying principles of Information Theory to improve the robustness and efficiency of SLAM techniques, and also investigation of algorithms for real-time operation on platforms with limited processing power.

For a brief introduction to visual SLAM and the basic principle of Active Matching, have a look at these notes.

Publications

REAL-TIME ONBOARD VISUAL-INERTIAL STATE ESTIMATION AND SELF-CALIBRATION OF MAVs IN UNKNOWN ENVIRONMENTS

Finalist for the best vision paper award

Stephan Weiss. Markus W. Achtelik, Simon Lynen, Margarita Chli and Roland Siegwart, "Real-time onboard Visual-Inertial state estimation and self-calibration of MAVs in unknown environments", in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2012.

{PDF, bibtex }

VERSATILE DISTRIBUTED POSE ESTIMATION AND SENSOR SELF-CALIBRATION FOR AN AUTONOMOUS MAV

Stephan Weiss. Markus W. Achtelik, Margarita Chli and Roland Siegwart, "Versatile Distributed Pose Estimation and Sensor Self-Calibration for an Autonomous MAV", in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2012.

{video, PDF, bibtex }

BRISK: BINARY ROBUST INVARIANT SCALABLE KEYPOINTS

Stefan Leutenegger, Margarita Chli and Roland Siegwart, "BRISK: Binary Robust Invariant Scalable Keypoints", in Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2011.

{video 1,video 2, PDF, CODE, bibtex }

ROBUST REAL-TIME VISUAL ODOMETRY WITH A SINGLE CAMERA AND AN IMU

Laurent Kneip, Margarita Chli and Roland Siegwart, "Robust Real-time Visual Odometry with a Single Camera and an IMU", in Proceedings of British Machine Vision Conference (BMVC) 2011.

{PDF, video, bibtex }

COLLABORATIVE STEREO

Markus Achtelik, Stephan Weiss, Margarita Chli, Frank Dellaert and Roland Siegwart, "Collaborative Stereo", in Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS) 2011.

{PDF,bibtex }

SCALABLE ACTIVE MATCHING

Ankur Handa, Margarita Chli, Hauke Strasdat and Andrew J. Davison, "Scalable Active Matching", in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010.

{PDF, video,poster,bibtex }

APPLYING INFORMATION THEORY TO EFFICIENT SLAM

Margarita Chli, "Applying Information Theory to Efficient SLAM", PhD Thesis, Imperial College London, 2009.

{PDF, bibtex, BMVA archive }

ACTIVE MATCHING FOR VISUAL TRACKING

 

Margarita Chli and Andrew J. Davison, "Active Matching for Visual Tracking", in Robotics and Autonomous Systems.

{PDF, ScienceDirect, related video, related SLIDES, bibtex }

AUTOMATICALLY AND EFFICIENTLY INFERRING THE HIERARCHICAL STRUCTURE OF VISUAL MAPS

Margarita Chli and Andrew J. Davison, "Automatically and Efficiently Inferring the Hierarchical Structure of Visual Maps", in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2009.

 { PDF,IEEE Xplore, video 1, video 2, SLIDES, bibtex }

ACTIVE MATCHING

Margarita Chli and Andrew J. Davison, "Active Matching", in Proceedings of the European Conference on Computer Vision (ECCV) 2008.

{ PDF, Springer, video, poster,related SLIDES, bibtex }