首页> 外文会议>Sensor Fusion and Aerospace Applications II >Application of neural networks to track association in over the horizon radar
【24h】

Application of neural networks to track association in over the horizon radar

机译:神经网络在超视距雷达跟踪关联中的应用

获取原文
获取原文并翻译 | 示例

摘要

Abstract: Over The Horizon Radar (OTHR) uses the ionospherelayers in the sky as a reflection medium. Multipleionospheric layers cause several tracks per target tobe observed at the receiver. The objective of thisresearch is to associate tracks which belong to thesame target. We adopt a data fusion approach to trackassociation which is based on knowledge of humanperceptual grouping mechanism -Gestalt psychology. Tofacilitate the fusion of the tracks by using affinityinformation derived from human perceptual groupingprinciples we developed a clustering algorithm based ona refined self-organizing neural network. This network,which we call the dynamic clustering scheme,automatically controls the allocation of clusters inresponse to the novelty of each input.!8
机译:摘要:地平线雷达(OTHR)使用天空中的电离层作为反射介质。多电离层导致在接收器上观察到每个目标的多个轨迹。本研究的目的是关联属于同一目标的轨道。我们采用一种基于人类感知分组机制-格式塔心理学的数据融合方法来进行轨迹关联。为了使用人类感知分组原则中的亲和力信息促进轨迹的融合,我们开发了一种基于精细自组织神经网络的聚类算法。我们将此网络称为动态聚类方案,它会根据每个输入的新颖性自动控制聚类的分配。8

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号