改进的D-S数据融合方法在车辆目标识别中的应用研究

Research on Application of Improved D-S Data Fusion in Vehicle Target Recognition

为了解决车辆目标识别的数据融合问题 ,本文引入了 Dempster- Shafer证据理论方法作为数据融合方法 ,并提出了时空数据融合的思想 ,把 D- S方法与时空数据融合的思想相结合 ,得到了时间域、空间域和时空域 D- S数据融合的方法 ,并用于目标识别中。通过实验得到经过融合后的识别结果比单传感器的识别结果要好 。

In order to find the most suitable method for target recognition under complex environment,hybrid data fusion method and its application are given. Through experiments and result analysis,itis proved that uti- lizing a hybrid structure of combination feature level and decision level is reasonable,and the method can be used for data fusion of target recognition under complex environment.