基于数据融合和多重智能模型的目标识别和跟踪

考虑到单传感器的系统存在着局限性，提出了基于多传感器（雷达和红外）信号融合的目标识别和跟踪系统，以利用数据的互补和冗余。特征层融合能利用各传感器提供的特征为提高目标识别能力；对于点目标和面目标分别提出了智能规则推理和神经网分类器的目标识别方法。决策层融合能提高目标跟踪的精度并提高抗干扰性；提出了可信度决策的目标跟踪方法。

Target Recognition and Tracking based on Data Fusion and Multiple Intelligent Models

This paper presents the approaches of multi sensor(radar and infrared sensor) data fusion for object recognition and tracking, which can make use of the complement and redundancy of data. The fusion of characteristics can combine characteristics from different sensors to improve the ability of object recognition. The approaches of object recognition based on inference of rules and neural classifier are presented to deal with the recognition of dot and surface. The fusion of strategic decision can improve the reliability and anti interference of object tracking, and an approach of object tracking based on the certainty of strategic decision is presented.