Associative and symbolic algorithms for viewpoint-independent object recognition

The authors address a specific problem related to image processing and understanding, i.e., recognition of three-dimensional (3-D) objects from a set of 2-D views. The chosen application is recognition of road scenes for semiautonomous vehicle driving. A recognition scheme is proposed that uses an associative mechanism as a guide sensor to estimate scene probabilities and probabilistic expectations of objects and their views in order to support a symbolic search process. Associative matching results are used to assess object probabilities of being present in the scene; such probabilities are utilized to define a top-down searching order to be followed by the symbolic recognition process. Some new results are reported on generation of specific keys for coding 2-D object views in associative memories