Determining the self-motion of a camera is useful for many applications. A number of visual motion-tracking
algorithms have been developed till date, each with their own advantages and restrictions. Some of them have
also made their foray into the mobile world, powering augmented reality-based applications on phones with inbuilt
cameras. In this paper, we compare the performances of three feature or landmark-guided motion tracking
algorithms, namely marker-based tracking with MXRToolkit, face tracking based on CamShift, and MonoSLAM.
We analyze and compare the complexity, accuracy, sensitivity, robustness and restrictions of each of the above
methods. Our performance tests are conducted over two stages: The first stage of testing uses video sequences
created with simulated camera movements along the six degrees of freedom in order to compare accuracy in
tracking, while the second stage analyzes the robustness of the algorithms by testing for manipulative factors
like image scaling and frame-skipping.