Paper Info
Title
Robust real-time tracking by fusing measurements from inertial and vision sensors
Abstract
Received: date / Revised: date Abstract The problem of estimating and predicting po- sition and orientation (pose) of a camera is approached by fusing measurements from inertial sensors (accelero- meters and rate gyroscopes) and vision. The sensor fu- sion approach described in this contribution is based on non-linear filtering of these complementary sensors. This way, accurate and robust pose estimates are available for the primary purpose of augmented reality applications, but with the secondary eect of reducing computation time and improving the performance in vision process- ing. A real-time implementation of a multi-rate extended Kalman filter is described, using a dynamic model with 22 states, where 100 Hz inertial measurements and 12.5 Hz correspondences from vision are processed. An example where an industrial robot is used to move the sensor unit is presented. The advantage with this configuration is that it provides ground truth for the pose, allowing for objective performance evaluation. The results show that we obtain an absolute accuracy of 2 cm in position and 1 in orientation.
Year
DOI
Venue
2007
10.1007/s11554-007-0040-2
J. Real-Time Image Processing
Keywords
Field
DocType
pose estimationsensor fusion � computer visioninertial navigation,technology,inertial navigation,ground truth,computer vision,pose estimation,sensor fusion,control engineering,augmented reality,extended kalman filter
Inertial navigation system,Computer vision,Extended Kalman filter,Gyroscope,Accelerometer,Computer science,Pose,Sensor fusion,Augmented reality,Real-time computing,Inertial measurement unit,Artificial intelligence
Journal
Volume
Issue
ISSN
2
2-3
1861-8219
Citations 
PageRank 
References 
22
0.91
24
Authors
5
Name
Order
Citations
PageRank
Jeroen D. Hol11068.50
Thomas B. Schön274472.66
Henk Luinge317925.05
Per J. Slycke41058.13
Fredrik Gustafsson52287281.33