A NEURAL MATCHING ALGORITHM FOR 3-D RECONSTRUCTION FROM STEREO PAIRS OF LINEAR IMAGES

In this paper, we propose a neural approach for obstacle detection in front of moving cars, using linear stereo vision. The key problem is t he so-called ''correspondence problem'' which consists in matching fea tures extracted from two images that are projections of the same entit y in the three-dimensional world. The linear stereo correspondence pro blem is first formulated as an optimization task where an energy funct ion, which represents the constraints on the solution, is to be minimi zed. The optimization problem is then performed by means of a Hopfield neural network. Experimental results, using real stereo images, demon strate the effectiveness of the method.