A moving target trajectory prediction method based on neighborhood fitting. Issue 1 (1st August 2022)

• Record Type: Journal Article
• Authors: He, Sihua; Liu, Chenghao; Li, Junhua
• Is Part Of: Journal of physics. Volume 2336:Issue 1(2022)
• Publication Date: 2022-08-01
• Subjects: Neighborhood -- Fitting -- Trajectory -- Prediction; Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2336/1/012019
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In order to solve the influence of time delay and data frame loss on the tracking accuracy of high mobility target, a moving target trajectory prediction method based on neighborhood fitting is proposed. The influence of neighborhood width, polynomial order and prediction steps on prediction accuracy are analyzed, and suggestions on parameter selection are given. Four typical moving target trajectories, such as parabola, climb line, spiral line and gyratory line are predicted. The experimental results show that the trajectory prediction method has high accuracy and good stability, and can meet the requirements of moving target tracking.