Monocular visual SLAM for small UAVs in GPS-denied environments
Authors:
- 1 December 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 896-901
Abstract
This paper presents a monocular visual simultaneous localization and mapping (SLAM) system for a small unmanned aerial vehicle (UAV) in GPS-denied environments. A single camera is used to measure the motion of the vehicle and detect features (landmarks) for the map building. The SLAM estimates the positions of the UAV and the features by an extended Kalman filter (EKF), which takes the velocity estimated by the fusion of the inertial and visual measurements as the input. An inverse depth method is adopted for the feature initialization. Both simulations and experiments are carried out to verify the effectiveness of this system.Keywords
This publication has 10 references indexed in Scilit:
- Monocular vision SLAM for indoor aerial vehicles2009
- Visual 3-D SLAM from UAVsJournal of Intelligent & Robotic Systems, 2009
- Inverse Depth Parametrization for Monocular SLAMIEEE Transactions on Robotics, 2008
- Vision-Based Odometry and SLAM for Medium and High Altitude Flying UAVsJournal of Intelligent & Robotic Systems, 2008
- MonoSLAM: Real-Time Single Camera SLAMIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- On the Observability of Bearing-only SLAM2007
- Inertial Aiding of Inverse Depth SLAM using a Monocular CameraProceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164), 2007
- Real-time implementation of airborne inertial-SLAMRobotics and Autonomous Systems, 2007
- Building a Robust Implementation of Bearing‐only Inertial SLAM for a UAVJournal of Field Robotics, 2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004