Abstract
A novel satellite target recognition method based on radar data partition and deep learning techniques is proposed in this paper. For the radar satellite recognition task, orbital altitude is introduced as a distinct and accessible feature to divide radar data. On this basis, we design a new distance metric for HRRPs called normalized angular distance divided by correlation coefficient (NADDCC), and a hierarchical clustering method based on this distance metric is applied to segment the radar observation angular domain. Using the above technology, the radar data partition is completed and multiple HRRP data clusters are obtained. To further mine the essential features in HRRPs, a GRU-SVM model is designed and firstly applied for radar HRRP target recognition. It consists of a multi-layer GRU neural network as a deep feature extractor and linear SVM as a classifier. By training, GRU neural network successfully extracts effective and highly distinguishable features of HRRPs, and feature visualization technology shows its advantages. Furthermore, the performance testing and comparison experiments also demonstrate that GRU neural network possesses better comprehensive performance for HRRP target recognition than LSTM neural network and conventional RNN, and the recognition performance of our method is almost better than that of other several common feature extraction methods or no data partition.
Highlights
Space target recognition is a primary function of space surveillance information systems, and satellite recognition is of critical importance on this study, especially for observation satellites
For the target-attitude sensitivity problem of high-resolution range profile (HRRP), we propose a hierarchical clustering method with a novel distance metric, namely the normalized angular distance divided by correlation coefficient (NADDCC), to segment radar observation angular domain
gated recurrent unit (GRU) neural network training, and a full comparative analysis of the recognition results under different different conditions and recognition methods is made
Summary
Space target recognition is a primary function of space surveillance information systems, and satellite recognition is of critical importance on this study, especially for observation satellites. An HRRP is the phasor sum of the time returns from different scatterers on the target located within a resolution cell [3], which represents the projection of the complex returned echoes from the target scattering centers onto the range axis [4]. It contains lots of geometric structure information about the target down range, such as scatterers distribution and target size. This paper focuses on the satellite target recognition based on radar data and proposes a novel recognition method, which mainly consists of data partition and deep learning model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
