Tracking methods are evaluated in a real-time feature tracking system used for human-computer interaction (HCI). The Camera Mouse, a HCI system for people with severe disabilities that interprets video input to manipulate the mouse pointer [1], was improved and used as the test platform for this study. Tracking methods tested are the Lucas-Kanade tracker [6] and a tracker based on normalized correlation [1]. Both methods are evaluated with and without multidimensional Kalman filters. Two-, four-, and six-dimensional filters are tested to model feature location, velocity, and acceleration. The various tracker and filter combinations are evaluated for accuracy, computational efficiency, and practiality. The normalized correlation coefficient tracker without Kalman filtering is found to be the tracker best suited for a variety of HCI tasks.