DocumentCode :
2689798
Title :
Visual odometry learning for unmanned aerial vehicles
Author :
Guizilini, Vitor ; Ramos, Fabio
Author_Institution :
Australian Centre for Field Robot., Univ. of Sydney, Sydney, NSW, Australia
fYear :
2011
fDate :
9-13 May 2011
Firstpage :
6213
Lastpage :
6220
Abstract :
This paper addresses the problem of using visual information to estimate vehicle motion (a.k.a. visual odometry) from a machine learning perspective. The vast majority of current visual odometry algorithms are heavily based on geometry, using a calibrated camera model to recover relative translation (up to scale) and rotation by tracking image features over time. Our method eliminates the need for a parametric model by jointly learning how image structure and vehicle dynamics affect camera motion. This is achieved with a Gaussian Process extension, called Coupled GP, which is trained in a supervised manner to infer the underlying function mapping optical flow to relative translation and rotation. Matched image features parameters are used as inputs and linear and angular velocities are the outputs in our non-linear multi-task regression problem. We show here that it is possible, using a single uncalibrated camera and establishing a first-order temporal dependency between frames, to jointly estimate not only a full 6 DoF motion (along with a full covariance matrix) but also relative scale, a non-trivial problem in monocular configurations. Experiments were performed with imagery collected with an unmanned aerial vehicle (UAV) flying over a deserted area at speeds of 100-120 km/h and altitudes of 80-100 m, a scenario that constitutes a challenge for traditional visual odometry estimators.
Keywords :
aircraft; distance measurement; image sequences; learning (artificial intelligence); regression analysis; remotely operated vehicles; Gaussian process; calibrated camera model; camera motion; coupled GP; function mapping optical flow; geometry; image features tracking; image structure; machine learning; nonlinear multitask regression problem; unmanned aerial vehicles; vehicle dynamics; vehicle motion; visual information; visual odometry learning; Cameras; Covariance matrix; Optical sensors; Training; Vehicles; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2011 IEEE International Conference on
Conference_Location :
Shanghai
ISSN :
1050-4729
Print_ISBN :
978-1-61284-386-5
Type :
conf
DOI :
10.1109/ICRA.2011.5979706
Filename :
5979706
Link To Document :
بازگشت