Multisensorial Vision For Autonomous Vehicle Driving

摘要: A multisensorial vision system for autonomous vehicle driving is presented, that operates in outdoor natural environments. The system, currently under development our laboratories, will be able to integrate data provided by different sensors order achieve a more reliable description of scene and meet safety requirements. We chose perform high-level symbolic fusion the better accomplish recognition task. knowledge-based approach followed, which provides accurate solution; particular, it possible both physical data, furnished each channel, strategies, using an appropriate control structure. high complexity integration reduced acquiring, filtering, segmenting extracting features from sensor channel. Production rules, divided into groups according specific goals, drive process, linking frame all segmented regions characterized similar properties. As first application, road obstacle detection performed. particular strategy tested integrates results separately obtained applying module related model description. Preliminary are very promising confirm validity proposed approach.