基于数据融合和多重智能模型的目标识别和跟踪  

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

作　　者：杨杰[1] 陆正刚[1] 郭英凯[1] 

机构地区：[1]上海交通大学图象处理和模式识别研究所

出　　处：《高技术通讯》1999年第4期10-14,共5页Chinese High Technology Letters

基　　金：国家自然科学基金;国防预研项目

摘　　要：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；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.

关 键 词：目标识别和跟踪 数据融合 模式识别 人工神经网 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP274.2[自动化与计算机技术—计算机科学与技术]