一种基于随机超曲面的扩展目标形状评估方法  

作　　者：徐寒 韩玉兰 曹晓峰 

机构地区：[1]宁夏大学物理与电子电气工程学院,宁夏银川750021

出　　处：《科技创新与应用》2022年第10期133-136,140,共5页Technology Innovation and Application

基　　金：国家自然科学基金(61863030);宁夏自然科学基金(2021AAC03061)。

摘　　要：随着传感器分辨率的不断提高,传统的点目标假设不再成立,目标跟踪的任务不仅仅是估计出目标的运动状态,更重要的是要对其扩展形状进行精确估计。对于运动状态估计的评估,有很多相应的指标可以实现,但是对目标的形状估计性能评估有着迫切的需求。针对基于随机超曲面的不规则的目标跟踪,提出一种基于径向函数的方法来解决对估计形状的评估问题。仿真实验表明,提出的方法能够作为一种有效的度量准则来对扩展目标的形态估计性能进行有效评估。With the continuous improvement of sensor resolution,the traditional point target hypothesis is no longer valid.The task of target tracking is not only to estimate the motion state of the target,but also to accurately estimate its extended shape.For the evaluation of motion state estimation,there are many corresponding indicators that can be achieved,but there is an urgent need to evaluate the performance of target shape estimation.Aiming at the irregular target tracking based on random hypersurface,a method based on radial function is proposed to evaluate the estimated shape.Simulation results show that the proposed method can be used as an effective metric criterion to effectively estimate the morphological estimation performance of extended targets.

关 键 词：扩展目标 随机超曲面模型 径向函数 形状估计 性能评估 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]