A morphological model-driven approach to real-time road boundary detection for vision-based automotive systems

This work presents a Computer Vision system for road boundary detection in automotive applications. Images are processed by a multiresolution algorithm, driven by a-priori knowledge through a top-down control. In order to face the hard real-time constraints of automotive tasks, a special purpose massively parallel computer architecture, PAPRICA, has been developed. The whole system is currently operative on MOB-LAB mobile laboratory: a land vehicle integrating the results of the activities of the Italian PROMETHEUS units. The basis of the algorithm is discussed using the formal tools of mathematical morphology, while the choice of the computing architecture and of the computational paradigm is explained. The generality of the presented approach allows its use also to solve similar problems, namely to detect features exploiting a long-distance correlation, such as the road boundaries in vehicular applications