This paper develops a color landmark-based global localization method for an indoor wheeled mobile robot using color CCD camera and dead-reckoning measurements.Based on the triangulation approach, the initial and global pose of the robot in any fiat environment is uniquely determined using a color CCD camera along with at least three given colorful landmarks.A fuzzy extended information filtering (FEIF) algorithm is employed to merge both visual and odometric measurements for improving the pose tracking accuracy of the robot while traveling over its working space.Several experiment results are provided to show the efficacy usefulness of the proposed global localization and pose tracking methods.