Fuzzy Operators for Confidence Modelling in Automotive Safety Applications

The fusion of data from different sensorial sources is the most promising method to increase robustness and reliability of environmental perception today. The paper presents an approach for using fuzzy operators for the hierarchical fusion of processing results in a multi sensor data processing system for the detection of vehicles in road environments. Tracking and fusion of intermediate results are performed in several levels of processing (signal level, several feature levels, object level). To produce higher level hypotheses on the basis of lower level components, grouping rules using certain assignment decisions are used. One example is given for the fusion of image and radar data in a vehicle detection algorithm used in a driver assistance system.