关键词：汽车；车辆的行驶状态;安全规则；BP神经网络；DS证据规则
摘 要：An evaluation system of vehicle traveling state was proposed,and an unsafe vehicle traveling state recognition system was established using multi-level information fusion method.In view of the effects of the complexity of the driving environment,a variety of working conditions and the diversity of vehicle traveling characteristics,combing BP neural network with Dempster Sharer evidence theory technique,the multi-information decision-level fusion was proposed to estimate the different kind model of the vehicle status.To verify the proposed strategies,the vehicle traveling posture evaluation system was established.The lane departure parameters and the relative distance parameters were studied in order to get the characterization of the vehicle traveling status information.The simulation results indicate that the adaptability and accuracy and the intelligence level of driving characterization estimation are significantly improved by using the pattern classification and decision technology of multi-source information fusion.