Short-term trajectory prediction of aerial target based on LSTM model

Yun Chen; Jie Zou; Mengjie Wu

doi:10.1117/12.2627642

11 March 2022 Short-term trajectory prediction of aerial target based on LSTM model

Yun Chen, Jie Zou, Mengjie Wu

Proceedings Volume 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021); 121600S (2022) https://doi.org/10.1117/12.2627642
Event: International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 2021, Sanya, China

Abstract

When the radar is tracking an air target, there is a short-term interruption of the track. The accurate prediction of the target track can help improve the accuracy of the track association. In response to the problem of low calculation accuracy of traditional track prediction algorithms, this article introduces and adopts a long short-term memory algorithm (Long Short − Term Memory) track prediction method. Use data to train the model, and use the mean square error (MSE) as an evaluation indicator to predict the future location of the target. The final simulation test results show that the algorithm can use the changing law of the air target's movement state to predict the target's movement state in a certain time in the future, which demonstrates the feasibility of the proposed algorithm in the problem of interrupted track prediction.

Citation Download Citation

Yun Chen, Jie Zou, and Mengjie Wu "Short-term trajectory prediction of aerial target based on LSTM model", Proc. SPIE 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 121600S (11 March 2022); https://doi.org/10.1117/12.2627642

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available