|
Descripción
|
|
|---|---|
| Self localization and motion estimation is a requisite skill for autonomous robots. It enables the robot to navigate autonomously without relying on external positioning systems. This can be achieved by making use of a stereo camera on board of the robot. In this work a stereo visual odometry algorithm is developed which uses FAST features in combination with the Rotated-BRIEF descriptor and an approach for feature tracking. For motion estimation we utilize 3D to 2D point correspondences as well as 2D to 2D point correspondences. First we estimate an initial relative pose by decomposing the essential matrix. After that we refine the initial motion estimate by solving an optimization problem that minimizes the reprojection error as well as a cost function based on the epipolar constraint. The second cost function enables us to take also advantage of useful information from 2D to 2D point correspondences. Finally we evaluate the implemented algorithm on the well known KITTI and EuRoC datasets. | |
|
Internacional
|
Si |
|
Nombre congreso
|
the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. |
|
Tipo de participación
|
960 |
|
Lugar del congreso
|
|
|
Revisores
|
Si |
|
ISBN o ISSN
|
978-989-758-290-5 |
|
DOI
|
|
|
Fecha inicio congreso
|
27/01/2018 |
|
Fecha fin congreso
|
29/01/2018 |
|
Desde la página
|
0 |
|
Hasta la página
|
0 |
|
Título de las actas
|
Combining 2D to 2D and 3D to 2D Point Correspondences in Stereo Visual Odometry |