Abstract
The threat of space targets is moving toward the diversification of attack forms and the speed of warfare. It is urgent to carry out research on space target monitoring and identification technology. The radar cross-sectional data is obtained by moving the spatial target along the orbit relative to the measured radar attitude, and the target stable state can be roughly inferred after the data processing, thereby constructing the target template library. In this paper, a neural network-based RCS sequence target recognition method is presented. The scheme of constructing the attitude angle template library by the angle between the radar line of sight and the target radial axis and tangential axis is proposed. Through feature extraction and classifier design, the 18-dimensional feature vector is composed of 18 features, and the neural network classifier is used for training and classification. The recognition accuracy of a sliding window processing can reach 96.77%, which achieves the ideal effect.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, B.: Analysis and Design of Modern Radar System. Xi’an University of Electronic Science and Technology Press, Xi’an (2016)
Deng, J.: Research on Measurement of Target Reflection Characteristics of Millimeter Wave Short Range Radar. Nanjing University of Science and Technology, Nanjing (2007)
Chen, L., et al.: Modeling and Detection of Typical Complex Micro-motion Targets. Telecommun. Technol. 56(11) (2016)
Shen, T.: Research and Discussion of Artificial Neural Network Based on Nonparametric Statistical Method. East China Normal University, Shanghai (2010)
Acknowledgements
This paper gives a method to build the target template, extract the 18-dimensional characteristics of the RCS sequence, construction of neural network in target recognition based on RCS sequence, the recognition accuracy of the test of 96.77%, the accuracy is a sliding window, through the continuous sliding window weighted average [5] for many times, can further improve the recognition of the time. Based on the current feature extraction and recognition framework, more data can be collected for verification in the future, and the features can be increased or decreased according to the statistical results, so as to achieve the ideal recognition results for the measured data.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Pan, G., Liang, S., Liu, S., Yong, X. (2021). Target Recognition of RCS Sequence Based on Neural Network. In: WU, C.H., PATNAIK, S., POPENTIU VLÃDICESCU, F., NAKAMATSU, K. (eds) Recent Developments in Intelligent Computing, Communication and Devices. ICCD 2019. Advances in Intelligent Systems and Computing, vol 1185. Springer, Singapore. https://doi.org/10.1007/978-981-15-5887-0_5
Download citation
DOI: https://doi.org/10.1007/978-981-15-5887-0_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-5886-3
Online ISBN: 978-981-15-5887-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)