Parametric models of shape and texture such as Active Appearance Models (AAMs) are diverse tools for deformable object appearance modeling and have found important applications in...
We present a novel geometrical constraint on the egomotion of a single, moving camera. Using a camera with a large field-of-view (FOV), the optical flow measured at a single pair ...
Conventional registration algorithms are mostly concerned with rigid-body transformation parameters between a pair of 3D range images. Our proposed framework aims to determine, in...
— Texture analysis plays an increasingly important role in computer vision. Since the textural properties of images appear to carry useful information for discrimination purposes...
Abstract Image alignment has been a long standing problem in computer vision. Parameterized Appearance Models (PAMs) such as the Lucas-Kanade method, Eigentracking, and Active Appe...