【摘要】 文章提出一种基于随机森林方法的航迹起始算法。本文将航迹起始问题视为监督学习中的分类问题,分为离线训练和在线起始两个阶段。在离线训练阶段,通过历史量测数据构建随机森林组合分类模型。在在线起始阶段,首先将环境中的量测数据经过简单规则法预处理得到测试样本,然后提取特征输入到训练完成的随机森林中,最后得到航迹起始的结果。通过仿真实验,将本文提出的方法和修正的Hough变换进行对比发现:本文提出的方法在重杂波、高量测噪声背景下有更好的性能。更多还原

【Abstract】 In this paper,the track initiation problem is regarded as a classification problem of supervised learning,which is divided into two stages:off-line training and on-line track initiation.In the off-line training stage,a random forest combination classification model is constructed through historical data.In the on-line initiation stage,firstly,the measured data in the environment are pretreated by simple rule method to get the test samples,then the extracted features are input into the trained random forest,and finally the track initiation results are obtained.The simulation results show that the proposed method has better performance in heavy clutter and high measurement noise compared with the modified Hough transform method.更多还原