Issue No. 12 - December (1992 vol. 14)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.177383
<p>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.</p>
disparity map refinement; camera motion recovery; self-calibration; incremental refinement; dynamic stereo sequence; binocular stereo vision system; mobile robot; robust least median of squares based algorithm; recursive disparity prediction; robust Kalman filter; calibration; filtering and prediction theory; image sequences; Kalman filters; least squares approximations; mobile robots; motion estimation; stereo image processing
B. Schunck, R. Jain and A. Tirumalai, "Dynamic Stereo with Self-Calibration," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 14, no. , pp. 1184-1189, 1992.