Multiple view geometry in computer visiond
Multiple view geometry in computer visiond
Jacobian Images of Super-Resolved Texture Maps for Model-Based Motion Estimation and Tracking
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Vision and Inertial Sensor Cooperation Using Gravity as a Vertical Reference
IEEE Transactions on Pattern Analysis and Machine Intelligence
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
An Invitation to 3-D Vision: From Images to Geometric Models
An Invitation to 3-D Vision: From Images to Geometric Models
An Efficient Solution to the Five-Point Relative Pose Problem
IEEE Transactions on Pattern Analysis and Machine Intelligence
Inertial Sensed Ego-motion for 3D Vision
Journal of Robotic Systems
MonoSLAM: Real-Time Single Camera SLAM
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Ego-motion Estimation with Multi-rate Fusion of Inertial and Vision
International Journal of Robotics Research
An Introduction to Inertial and Visual Sensing
International Journal of Robotics Research
Relative Pose Calibration Between Visual and Inertial Sensors
International Journal of Robotics Research
Hi-index | 0.00 |
Unmanned miniature air vehicles (MAVs) have recently become a focus of much research, due to their potential utility in a number of information gathering applications. MAVs currently carry inertial sensor packages that allow them to perform basic flight maneuvers reliably in a completely autonomous manner. However, MAV navigation requires knowledge of location that is currently available only through GPS sensors, which depend on an external infrastructure and are thus prone to reliability issues. Vision-based methods such as Visual Odometry (VO) have been developed that are capable of estimating MAV pose purely from vision, and thus have the potential to provide an autonomous alternative to GPS for MAV navigation. Because VO estimates pose by combining relative pose estimates, constraining relative pose error is the key element of any Visual Odometry system. In this paper, we present a system that fuses measurements from an MAV inertial navigation system (INS) with a novel VO framework based on direct image registration. We use the inertial sensors in the measurement step of the Extended Kalman Filter to determine the direction of gravity, and hence provide error-bounded measurements of certain portions of the aircraft pose. Because of the relative nature of VO measurements, we use VO in the EKF prediction step. To allow VO to be used as a prediction, we develop a novel linear approximation to the direct image registration procedure that allows us to propagate the covariance matrix at each time step. We present offline results obtained from our pose estimation system using actual MAV flight data. We show that fusion of VO and INS measurements greatly improves the accuracy of pose estimation and reduces the drift compared to unaided VO during medium-length (tens of seconds) periods of GPS dropout.