基于支持向量机分类决策的行人导航零速修正方法
DOI:
作者:
作者单位:

郑州轻工业学院电气信息工程学院,郑州轻工业学院电气信息工程学院,郑州轻工业学院电气信息工程学院,郑州轻工业学院电气信息工程学院,郑州轻工业学院电气信息工程学院,郑州轻工业学院电气信息工程学院,郑州轻工业学院电气信息工程学院

作者简介:

通讯作者:

中图分类号:

V249.32

基金项目:

河南省科技攻关项目


Research on Pedestrian Navigation Zero-speed Correction Method Based on SVM Classification Decision
Author:
Affiliation:

School of Electrical and Information Engineering,Zhengzhou University of Light Industry,School of Electrical and Information Engineering,Zhengzhou University of Light Industry,School of Electrical and Information Engineering,Zhengzhou University of Light Industry,School of Electrical and Information Engineering,Zhengzhou University of Light Industry,School of Electrical and Information Engineering,Zhengzhou University of Light Industry,School of Electrical and Information Engineering,Zhengzhou University of Light Industry,School of Electrical and Information Engineering,Zhengzhou University of Light Industry

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了减小行人导航过程中的误差,提出基于支持向量机分类决策的零速反馈修正方法。根据行人足部运动特点,构建行人足部运动模型,利用支持向量机决策方法对足部运动样本数据进行训练和提取数据特征,建立超平面方程。通过超平面函数对行人足部运动数据进行分类和决策,辨别区分静止段和运动段。在零速静止段,对惯性导航解算的速度、角速度和方向进行修正,利用扩展卡尔曼滤波递推方法进行方向、速度和位置误差跟踪。进行了行人按既定路径的行走跟踪实验,结果表明,设计的行人导航系统能够使行人行走轨迹与设定路径完全吻合,多次测试数据最大误差小于2.5%,平均误差为1.94%。因此,基于支持向量机分类决策的行人导航零速修正方法能够准确地对行人轨迹进行跟踪和定位。

    Abstract:

    IIn order to reduce the error in the pedestrian navigation process, a zero-speed feedback correction method based on support vector machine classification decision is proposed. According to the characteristics of pedestrian foot movement, the pedestrian foot motion model is constructed. The support vector machine decision method is used to train the foot motion sample data and extract the data features to construct the hyperplane equation. The classification and decision of pedestrian foot motion data are classified by the hyperplane function, and the stationary segment and the motion segment are distinguished. In the zero-speed stationary section, the speed, angular velocity and direction of the inertial navigation solution are corrected, and the extended Kalman filter recursive method is used to track the direction, velocity and position error. The walking tracking experiment of pedestrians according to the established path is carried out. The results show that the pedestrian navigation system can make the pedestrian walking trajectory completely match the set path. The maximum error of multiple test data is less than 2.5%, and the average error is 1.94%. Therefore, the pedestrian navigation zero-speed correction method based on support vector machine classification decision can accurately track and locate the pedestrian trajectory.

    参考文献
    相似文献
    引证文献
引用本文

王晓雷,闫双建,李栋豪,等. 基于支持向量机分类决策的行人导航零速修正方法[J]. 科学技术与工程, 2019, 19(1): .
WANG Xiao-lei, YAN Shuang-jian, LI Dong-hao, et al. Research on Pedestrian Navigation Zero-speed Correction Method Based on SVM Classification Decision[J]. Science Technology and Engineering,2019,19(1).

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2018-09-08
  • 最后修改日期:2018-11-05
  • 录用日期:2018-11-09
  • 在线发布日期: 2019-01-15
  • 出版日期:
×
律回春渐,新元肇启|《科学技术与工程》编辑部恭祝新岁!
亟待确认版面费归属稿件,敬请作者关注