My ICIP 2006 Schedule
Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
|Time:||Wednesday, October 11, 09:40 - 12:20
|| Motion Detection and Estimation: Parametric models for motion estimation|
|| STEREO TRACKING AND THREE-POINT/ONE-POINT ALGORITHMS - A ROBUST APPROACH IN VISUAL ODOMETRY|
||Kai Ni; Georgia Institute of Technology|| |
| ||Frank Dellaert; Georgia Institute of Technology|| |
|| In this paper, we present an approach of calculating visual odometry for outdoor robots equipped with a stereo rig. Instead of the typical feature matching or tracking, we use an improved stereo-tracking method that simultaneously decides the feature displacement in both cameras. Based on the matched features, a three-point algorithm for the resulting quadrifocal setting is carried out in a RANSAC framework to recover the unknown odometry. In addition, the change in rotation can be derived from infinity homography, and the remaining translational unknowns can be obtained even faster consequently . Both approaches are quite robust and deal well with challenging conditions such as wheel slippage.|