From multiple views to object recognition

A computational method is presented for recovering 3-D shapes by exploiting multiple views of an object. The method provides a volumetric representation of the object starting from the occluding contours, i.e., the contours which separate the object image from the background. A detailed description of the geometrical transformations applied to build the volumetric representation of objects from multiple occluding contours of real images is reported. The only input parameters necessary are the orientation of the TV cameras used. The volumetric representation obtained is recognized by matching it with a library of models. Object recognition is performed in two steps. In the first step, some 3-D global structure parameters are used. If these are not sufficient to unambiguously recognize the object, in the second step the candidates chosen among the models are projected into the image planes of the TV cameras, and some 2-D features are used to perform the recognition, The models can be built either by means of a CAD technique or via the same method used to reconstruct the volumetric representation of the object.