Subspace Methods for Robot Vision 1

In contrast to the traditional approach, visual recognition is formulated as one of matching appearance rather than shape. For any given robot vision task, all possible appearance variations de ne its visual workspace. A set of images is obtained by coarsely sampling the workspace. The image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the visual workspace is represented as a continuous appearance manifold. Given an unknown input image, the recognition system rst projects the image to eigenspace. The parameters of the vision task are recognized based on the exact location of the projection on the appearance manifold. E cient algorithms for nding the closest manifold point are discussed. The proposed appearance representation has several applications in robot vision. As examples, a precise visual positioning system, a real-time visual tracking system, and a real-time temporal inspection system are described. The performance of these systems is evaluated through numerous experiments. The simplicity and generality of the proposed ideas have led to the development of a comprehensive software library for appearance modeling and matching. i