论文部分内容阅读
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信息来提高目标识别能力；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
Considering the limitations of the single sensor system, a target recognition and tracking system based on multi-sensor (radar and infrared) signal fusion is proposed to utilize the data complementarity and redundancy. The feature layer fusion can use the feature information provided by each sensor to improve the target recognition ability. For the point target and the surface target, the intelligent rule reasoning and the neural network target recognition method are proposed respectively. The fusion of decision-making layers can improve the accuracy of target tracking and improve the anti-interference ability. The target tracking method of credibility decision is proposed