Abnormal Dynamic Recognition of Space Targets From ISAR Image Sequences With SSAE-LSTM Network
- 6 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-16
Abstract
Abnormal dynamics awareness of space targets is critical for space surveillance. With the intrinsic range-Doppler projection mechanism, an inverse synthetic aperture radar (ISAR) image sequence naturally has crucial potential for abnormal dynamics interpretation on uncooperative targets. In this paper, we develop an automated deep neural network architecture for abnormal dynamic recognition of space targets from ISAR image sequences. With the accommodation of the stacked sparse autoencoder (SSAE) network joint sparsity constraint, the geometrical feature flow of an ISAR image sequence is learned to represent the target dynamics concisely. Then, the abnormal dynamic recognition is turned into a sequential classification task by exploiting the encoded feature flow through the long-short time memory (LSTM) network. Extensive experiment results confirm the superiority of the proposal in both precision and efficiency aspects.Keywords
Funding Information
- National Natural Science Foundation of China (62101603, 62201623)
- Shenzhen Science and Technology Program (KQTD20190929172704911)
- Introduced Innovative Research and Development Team Project of “The Pearl River Talent Recruitment Program” (2019ZT08X751)
This publication has 36 references indexed in Scilit:
- The attitude estimation of three-axis stabilized satellites using hybrid particle swarm optimization combined with radar cross section precise predictionProceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 2015
- Earth’s gravity gradient and eddy currents effects on the rotational dynamics of space debris objects: Envisat case studyAdvances In Space Research, 2015
- Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology ImagesIEEE Transactions on Medical Imaging, 2015
- A 3-D Electromagnetic-Model-Based Algorithm for Absolute Attitude Measurement Using Wideband RadarIEEE Geoscience and Remote Sensing Letters, 2015
- Simulation of ISAR Imaging for a Space Target and Reconstruction Under Sparse Sampling via Compressed SensingIEEE Transactions on Geoscience and Remote Sensing, 2015
- Attitude and Spin Period of Space Debris Envisat Measured by Satellite Laser RangingIEEE Transactions on Geoscience and Remote Sensing, 2014
- High-Resolution Fully Polarimetric ISAR Imaging Based on Compressive SensingIEEE Transactions on Geoscience and Remote Sensing, 2014
- The space situational awareness program of the European Space AgencyCosmic Research, 2010
- Long Short-Term MemoryNeural Computation, 1997
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992