Title :
Dynamic stereo with self-calibration
Author :
Tirumalai, Arun P. ; Schunck, Brian G. ; Jain, Ramesh C.
Author_Institution :
Dept. of Comput. Sci., South Carolina Univ., Columbia, SC, USA
fDate :
12/1/1992 12:00:00 AM
Abstract :
An approach for incremental refinement of disparity maps obtained from a dynamic stereo sequence of a static scene is presented. The approach has been implemented using a binocular stereo vision system mounted on a mobile robot. A robust least median of squares based algorithm is given for recovering the camera motion between successive viewpoints, which provides a self-calibration mechanism. The recovered motion is utilized for recursive disparity prediction and refinement using a robust Kalman filter model
Keywords :
Kalman filters; calibration; filtering and prediction theory; image sequences; least squares approximations; mobile robots; motion estimation; stereo image processing; binocular stereo vision system; camera motion recovery; disparity map refinement; dynamic stereo sequence; incremental refinement; mobile robot; recursive disparity prediction; robust Kalman filter; robust least median of squares based algorithm; self-calibration; Cameras; Kalman filters; Laboratories; Layout; Mobile robots; Motion estimation; Recursive estimation; Robot vision systems; Robustness; Stereo vision;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
