In 2D images of 3D objects it is not possible to account for 3D viewpoint invariance as those invariant relations cannot be found. Therefore, a process of rapid hypothesis and verification is required in which the perceptual groupings of curvilinear features provide the hypotheses for verification by back-projection of the model data. In this paper, we present one approach to this latter cycle, using model representations having both straight and curved elements. We have described a practical approach to match 2D scenes to 3D models in which the scene data is described as a set of curvilinear features extracted from a grey scale image of a rigid object taken from an arbitrary viewpoint, and the model data is derived from a CSG modeller.
|Number of pages||5|
|Journal||IEE Conference Publication|
|Publication status||Published - 1989|
|Event||3rd International Conference on Image Processing and its Applications - Coventry, United Kingdom|
Duration: 18 Jul 1989 → 20 Jul 1989