Binocular camera fixation refers to the control of camera movements so that the optical axes of two cameras converge at a single point of interest in a three-dimensional scene. This thesis describes the theory and high-level algorithms for a procedure that can locate fixation points in an image pair. The binocular fixation procedure which has been developed here combats several difficult fixation problems that are hard to overcome with traditional approaches. Examples of this are objects lacking in visual texture, scenes with occluding conditions, repeating patterns, and objects which are steeply slanted with respect to the image planes. In order to deal with low-contrast image regions, the system is capable of detecting nearby salient points and shifting attention to a new salient target. Based on local image information, the system adaptively determines an initial window size using an Autoregressive-Moving Average (ARMA) modeling technique. Area-based feature matching is performed using normalized cross-covariance within a multiresolution image hierarchy. Gaussian low-pass filters of increasing spatial resolution are used to construct the hierarchy, and matching is performed in coarse-to-fine order. Finally, affine image warping is used in some cases to reduce the effects of perspective distortion so that area based image comparison is improved. The method presented here can serve as the foundation of a stereo tracking system, and has potential applications in such areas as autonomous vehicle navigation, industrial process control, and visually guided robot manipulation. / Master of Science