Visual Recognition of Obstacles on Roads

Abstract

Obstacle recognition is an essential subtask of a driver support system. According to a concept for obstacle recognition, the task should be decomposed into several largely independent subtasks, or modules, including the initial detection of possible obstacle candidates, the classification of obstacle candidates into false alarms (caused, for example, by shadows) and real physical objects, the tracking of obstacles, etc. As part of a driver support system for motor vehicles on freeways, an obstacle recognition system was developed within the EUREKA project PROMETHEUS over the last four years. The obstacle recognition system uses a single monochrome TV camera and a multiprocessor robot vision system. The recognition system includes a road tracker and an obstacle detector, and an object classification and tracking module. The module is based on generic 2D object models. It recognizes obstacles in real time and from distances of 200 to 300 m, sufficient for high-speed driving. The module was extensively tested in real-world scenes on the German autobahn and on various other roads, including city streets with heavy traffic.