VISION-BASED ROAD DETECTION IN AUTOMOTIVE SYSTEMS - A REAL-TIME EXPECTATION-DRIVEN APPROACH

The main aim of this work is the development of a vision-based road de tection system fast enough to cope with the difficult real-time constr aints imposed by moving vehicle applications. The hardware platform, a special-purpose massively parallel system, has been chosen to minimiz e system production and operational costs. This paper presents a novel approach to expectation-driven low-level image segmentation, which ca n be mapped naturally onto mesh-connected massively parallel SIMD arch itectures capable of handling hierarchical data structures. The input image is assumed to contain a distorted version of a given template; a multiresolution stretching process is used to reshape the original te mplate in accordance with the acquired image content, minimizing a pot ential function. The distorted template is the process output.