ALIGNMENT BY MAXIMIZATION OF MUTUAL INFORMATION

A new information-theoretic approach is presented for finding the pose of an object in an image. The technique does not require information about the surface properties of the object, besides its shape, and is robust with respect to variations of illumination. In our derivation f ew assumptions are made about the nature of the imaging process. As a result the algorithms are quite general and may foreseeably be used in a wide variety of imaging situations. Experiments are presented that demonstrate the approach registering magnetic resonance (MR) images, a ligning a complex 3D object model to real scenes including clutter and occlusion, tracking a human head in a video sequence and aligning a v iew-based 2D object model to real images. The method is based on a for mulation of the mutual information between the model and the image. As applied here the technique is intensity-based, rather than feature-ba sed. It works well in domains where edge or gradient-magnitude based m ethods have difficulty, yet it is more robust than traditional correla tion. Additionally, it has an efficient implementation that is based o n stochastic approximation.